zhao.zhu/yolov26_3d
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

单目3D初始代码

Browse Source
This commit is contained in:
zhao.zhu
2026-06-24 09:35:46 +08:00
commit 04a5895b6b
1153 changed files with 340700 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1030
ultralytics/cfg/__init__.py Executable file
View File

File diff suppressed because it is too large Load Diff

78
ultralytics/cfg/datasets/Argoverse.yaml Executable file
View File

@@ -0,0 +1,78 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Argoverse-HD dataset (ring-front-center camera) by Argo AI: https://www.cs.cmu.edu/~mengtial/proj/streaming/
# Documentation: https://docs.ultralytics.com/datasets/detect/argoverse/
# Example usage: yolo train data=Argoverse.yaml
# parent
# ├── ultralytics
# └── datasets
# └── Argoverse ← downloads here (31.5 GB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: Argoverse # dataset root dir
train: Argoverse-1.1/images/train/ # train images (relative to 'path') 39384 images
val: Argoverse-1.1/images/val/ # val images (relative to 'path') 15062 images
test: Argoverse-1.1/images/test/ # test images (optional) https://eval.ai/web/challenges/challenge-page/800/overview
# Classes
names:
0: person
1: bicycle
2: car
3: motorcycle
4: bus
5: truck
6: traffic_light
7: stop_sign
# Download script/URL (optional) ---------------------------------------------------------------------------------------
download: |
import json
from pathlib import Path
from ultralytics.utils import TQDM
from ultralytics.utils.downloads import download
def argoverse2yolo(annotation_file):
"""Convert Argoverse dataset annotations to YOLO format for object detection tasks."""
labels = {}
with open(annotation_file, encoding="utf-8") as f:
a = json.load(f)
for annot in TQDM(a["annotations"], desc=f"Converting {annotation_file} to YOLO format..."):
img_id = annot["image_id"]
img_name = a["images"][img_id]["name"]
img_label_name = f"{Path(img_name).stem}.txt"
cls = annot["category_id"] # instance class id
x_center, y_center, width, height = annot["bbox"]
x_center = (x_center + width / 2) / 1920.0 # offset and scale
y_center = (y_center + height / 2) / 1200.0 # offset and scale
width /= 1920.0 # scale
height /= 1200.0 # scale
img_dir = annotation_file.parents[2] / "Argoverse-1.1" / "labels" / a["seq_dirs"][a["images"][annot["image_id"]]["sid"]]
if not img_dir.exists():
img_dir.mkdir(parents=True, exist_ok=True)
k = str(img_dir / img_label_name)
if k not in labels:
labels[k] = []
labels[k].append(f"{cls} {x_center} {y_center} {width} {height}\n")
for k in labels:
with open(k, "w", encoding="utf-8") as f:
f.writelines(labels[k])
# Download 'https://argoverse-hd.s3.us-east-2.amazonaws.com/Argoverse-HD-Full.zip' (deprecated S3 link)
dir = Path(yaml["path"]) # dataset root dir
urls = ["https://drive.google.com/file/d/1st9qW3BeIwQsnR0t8mRpvbsSWIo16ACi/view?usp=drive_link"]
print("\n\nWARNING: Argoverse dataset MUST be downloaded manually, autodownload will NOT work.")
print(f"WARNING: Manually download Argoverse dataset '{urls[0]}' to '{dir}' and re-run your command.\n\n")
# download(urls, dir=dir)
# Convert
annotations_dir = "Argoverse-HD/annotations/"
(dir / "Argoverse-1.1" / "tracking").rename(dir / "Argoverse-1.1" / "images") # rename 'tracking' to 'images'
for d in "train.json", "val.json":
argoverse2yolo(dir / annotations_dir / d) # convert Argoverse annotations to YOLO labels

37
ultralytics/cfg/datasets/DOTAv1.5.yaml Executable file
View File

@@ -0,0 +1,37 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# DOTA 1.5 dataset https://captain-whu.github.io/DOTA/index.html for object detection in aerial images by Wuhan University
# Documentation: https://docs.ultralytics.com/datasets/obb/dota-v2/
# Example usage: yolo train model=yolov8n-obb.pt data=DOTAv1.5.yaml
# parent
# ├── ultralytics
# └── datasets
# └── dota1.5 ← downloads here (2 GB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: DOTAv1.5 # dataset root dir
train: images/train # train images (relative to 'path') 1411 images
val: images/val # val images (relative to 'path') 458 images
test: images/test # test images (optional) 937 images
# Classes for DOTA 1.5
names:
0: plane
1: ship
2: storage tank
3: baseball diamond
4: tennis court
5: basketball court
6: ground track field
7: harbor
8: bridge
9: large vehicle
10: small vehicle
11: helicopter
12: roundabout
13: soccer ball field
14: swimming pool
15: container crane
# Download script/URL (optional)
download: https://github.com/ultralytics/assets/releases/download/v0.0.0/DOTAv1.5.zip

36
ultralytics/cfg/datasets/DOTAv1.yaml Executable file
View File

@@ -0,0 +1,36 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# DOTA 1.0 dataset https://captain-whu.github.io/DOTA/index.html for object detection in aerial images by Wuhan University
# Documentation: https://docs.ultralytics.com/datasets/obb/dota-v2/
# Example usage: yolo train model=yolov8n-obb.pt data=DOTAv1.yaml
# parent
# ├── ultralytics
# └── datasets
# └── dota1 ← downloads here (2 GB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: DOTAv1 # dataset root dir
train: images/train # train images (relative to 'path') 1411 images
val: images/val # val images (relative to 'path') 458 images
test: images/test # test images (optional) 937 images
# Classes for DOTA 1.0
names:
0: plane
1: ship
2: storage tank
3: baseball diamond
4: tennis court
5: basketball court
6: ground track field
7: harbor
8: bridge
9: large vehicle
10: small vehicle
11: helicopter
12: roundabout
13: soccer ball field
14: swimming pool
# Download script/URL (optional)
download: https://github.com/ultralytics/assets/releases/download/v0.0.0/DOTAv1.zip

68
ultralytics/cfg/datasets/GlobalWheat2020.yaml Executable file
View File

@@ -0,0 +1,68 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Global Wheat 2020 dataset https://www.global-wheat.com/ by University of Saskatchewan
# Documentation: https://docs.ultralytics.com/datasets/detect/globalwheat2020/
# Example usage: yolo train data=GlobalWheat2020.yaml
# parent
# ├── ultralytics
# └── datasets
# └── GlobalWheat2020 ← downloads here (7.0 GB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: GlobalWheat2020 # dataset root dir
train: # train images (relative to 'path') 3422 images
- images/arvalis_1
- images/arvalis_2
- images/arvalis_3
- images/ethz_1
- images/rres_1
- images/inrae_1
- images/usask_1
val: # val images (relative to 'path') 748 images (WARNING: train set contains ethz_1)
- images/ethz_1
test: # test images (optional) 1276 images
- images/utokyo_1
- images/utokyo_2
- images/nau_1
- images/uq_1
# Classes
names:
0: wheat_head
# Download script/URL (optional) ---------------------------------------------------------------------------------------
download: |
from pathlib import Path
from ultralytics.utils.downloads import download
# Download
dir = Path(yaml["path"]) # dataset root dir
urls = [
"https://zenodo.org/record/4298502/files/global-wheat-codalab-official.zip",
"https://github.com/ultralytics/assets/releases/download/v0.0.0/GlobalWheat2020_labels.zip",
]
download(urls, dir=dir)
# Make Directories
for p in "annotations", "images", "labels":
(dir / p).mkdir(parents=True, exist_ok=True)
# Move
for p in (
"arvalis_1",
"arvalis_2",
"arvalis_3",
"ethz_1",
"rres_1",
"inrae_1",
"usask_1",
"utokyo_1",
"utokyo_2",
"nau_1",
"uq_1",
):
(dir / "global-wheat-codalab-official" / p).rename(dir / "images" / p) # move to /images
f = (dir / "global-wheat-codalab-official" / p).with_suffix(".json") # json file
if f.exists():
f.rename((dir / "annotations" / p).with_suffix(".json")) # move to /annotations

32
ultralytics/cfg/datasets/HomeObjects-3K.yaml Executable file
View File

@@ -0,0 +1,32 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# HomeObjects-3K dataset by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/detect/homeobjects-3k/
# Example usage: yolo train data=HomeObjects-3K.yaml
# parent
# ├── ultralytics
# └── datasets
# └── homeobjects-3K ← downloads here (390 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: homeobjects-3K # dataset root dir
train: images/train # train images (relative to 'path') 2285 images
val: images/val # val images (relative to 'path') 404 images
# Classes
names:
0: bed
1: sofa
2: chair
3: table
4: lamp
5: tv
6: laptop
7: wardrobe
8: window
9: door
10: potted plant
11: photo frame
# Download script/URL (optional)
download: https://github.com/ultralytics/assets/releases/download/v0.0.0/homeobjects-3K.zip

2025
ultralytics/cfg/datasets/ImageNet.yaml Executable file
View File

File diff suppressed because it is too large Load Diff

447
ultralytics/cfg/datasets/Objects365.yaml Executable file
View File

@@ -0,0 +1,447 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Objects365 dataset https://www.objects365.org/ by Megvii
# Documentation: https://docs.ultralytics.com/datasets/detect/objects365/
# Example usage: yolo train data=Objects365.yaml
# parent
# ├── ultralytics
# └── datasets
# └── Objects365 ← downloads here (712 GB = 367G data + 345G zips)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: Objects365 # dataset root dir
train: images/train # train images (relative to 'path') 1742289 images
val: images/val # val images (relative to 'path') 80000 images
test: # test images (optional)
# Classes
names:
0: Person
1: Sneakers
2: Chair
3: Other Shoes
4: Hat
5: Car
6: Lamp
7: Glasses
8: Bottle
9: Desk
10: Cup
11: Street Lights
12: Cabinet/shelf
13: Handbag/Satchel
14: Bracelet
15: Plate
16: Picture/Frame
17: Helmet
18: Book
19: Gloves
20: Storage box
21: Boat
22: Leather Shoes
23: Flower
24: Bench
25: Potted Plant
26: Bowl/Basin
27: Flag
28: Pillow
29: Boots
30: Vase
31: Microphone
32: Necklace
33: Ring
34: SUV
35: Wine Glass
36: Belt
37: Monitor/TV
38: Backpack
39: Umbrella
40: Traffic Light
41: Speaker
42: Watch
43: Tie
44: Trash bin Can
45: Slippers
46: Bicycle
47: Stool
48: Barrel/bucket
49: Van
50: Couch
51: Sandals
52: Basket
53: Drum
54: Pen/Pencil
55: Bus
56: Wild Bird
57: High Heels
58: Motorcycle
59: Guitar
60: Carpet
61: Cell Phone
62: Bread
63: Camera
64: Canned
65: Truck
66: Traffic cone
67: Cymbal
68: Lifesaver
69: Towel
70: Stuffed Toy
71: Candle
72: Sailboat
73: Laptop
74: Awning
75: Bed
76: Faucet
77: Tent
78: Horse
79: Mirror
80: Power outlet
81: Sink
82: Apple
83: Air Conditioner
84: Knife
85: Hockey Stick
86: Paddle
87: Pickup Truck
88: Fork
89: Traffic Sign
90: Balloon
91: Tripod
92: Dog
93: Spoon
94: Clock
95: Pot
96: Cow
97: Cake
98: Dining Table
99: Sheep
100: Hanger
101: Blackboard/Whiteboard
102: Napkin
103: Other Fish
104: Orange/Tangerine
105: Toiletry
106: Keyboard
107: Tomato
108: Lantern
109: Machinery Vehicle
110: Fan
111: Green Vegetables
112: Banana
113: Baseball Glove
114: Airplane
115: Mouse
116: Train
117: Pumpkin
118: Soccer
119: Skiboard
120: Luggage
121: Nightstand
122: Tea pot
123: Telephone
124: Trolley
125: Head Phone
126: Sports Car
127: Stop Sign
128: Dessert
129: Scooter
130: Stroller
131: Crane
132: Remote
133: Refrigerator
134: Oven
135: Lemon
136: Duck
137: Baseball Bat
138: Surveillance Camera
139: Cat
140: Jug
141: Broccoli
142: Piano
143: Pizza
144: Elephant
145: Skateboard
146: Surfboard
147: Gun
148: Skating and Skiing shoes
149: Gas stove
150: Donut
151: Bow Tie
152: Carrot
153: Toilet
154: Kite
155: Strawberry
156: Other Balls
157: Shovel
158: Pepper
159: Computer Box
160: Toilet Paper
161: Cleaning Products
162: Chopsticks
163: Microwave
164: Pigeon
165: Baseball
166: Cutting/chopping Board
167: Coffee Table
168: Side Table
169: Scissors
170: Marker
171: Pie
172: Ladder
173: Snowboard
174: Cookies
175: Radiator
176: Fire Hydrant
177: Basketball
178: Zebra
179: Grape
180: Giraffe
181: Potato
182: Sausage
183: Tricycle
184: Violin
185: Egg
186: Fire Extinguisher
187: Candy
188: Fire Truck
189: Billiards
190: Converter
191: Bathtub
192: Wheelchair
193: Golf Club
194: Briefcase
195: Cucumber
196: Cigar/Cigarette
197: Paint Brush
198: Pear
199: Heavy Truck
200: Hamburger
201: Extractor
202: Extension Cord
203: Tong
204: Tennis Racket
205: Folder
206: American Football
207: earphone
208: Mask
209: Kettle
210: Tennis
211: Ship
212: Swing
213: Coffee Machine
214: Slide
215: Carriage
216: Onion
217: Green beans
218: Projector
219: Frisbee
220: Washing Machine/Drying Machine
221: Chicken
222: Printer
223: Watermelon
224: Saxophone
225: Tissue
226: Toothbrush
227: Ice cream
228: Hot-air balloon
229: Cello
230: French Fries
231: Scale
232: Trophy
233: Cabbage
234: Hot dog
235: Blender
236: Peach
237: Rice
238: Wallet/Purse
239: Volleyball
240: Deer
241: Goose
242: Tape
243: Tablet
244: Cosmetics
245: Trumpet
246: Pineapple
247: Golf Ball
248: Ambulance
249: Parking meter
250: Mango
251: Key
252: Hurdle
253: Fishing Rod
254: Medal
255: Flute
256: Brush
257: Penguin
258: Megaphone
259: Corn
260: Lettuce
261: Garlic
262: Swan
263: Helicopter
264: Green Onion
265: Sandwich
266: Nuts
267: Speed Limit Sign
268: Induction Cooker
269: Broom
270: Trombone
271: Plum
272: Rickshaw
273: Goldfish
274: Kiwi fruit
275: Router/modem
276: Poker Card
277: Toaster
278: Shrimp
279: Sushi
280: Cheese
281: Notepaper
282: Cherry
283: Pliers
284: CD
285: Pasta
286: Hammer
287: Cue
288: Avocado
289: Hami melon
290: Flask
291: Mushroom
292: Screwdriver
293: Soap
294: Recorder
295: Bear
296: Eggplant
297: Board Eraser
298: Coconut
299: Tape Measure/Ruler
300: Pig
301: Showerhead
302: Globe
303: Chips
304: Steak
305: Crosswalk Sign
306: Stapler
307: Camel
308: Formula 1
309: Pomegranate
310: Dishwasher
311: Crab
312: Hoverboard
313: Meatball
314: Rice Cooker
315: Tuba
316: Calculator
317: Papaya
318: Antelope
319: Parrot
320: Seal
321: Butterfly
322: Dumbbell
323: Donkey
324: Lion
325: Urinal
326: Dolphin
327: Electric Drill
328: Hair Dryer
329: Egg tart
330: Jellyfish
331: Treadmill
332: Lighter
333: Grapefruit
334: Game board
335: Mop
336: Radish
337: Baozi
338: Target
339: French
340: Spring Rolls
341: Monkey
342: Rabbit
343: Pencil Case
344: Yak
345: Red Cabbage
346: Binoculars
347: Asparagus
348: Barbell
349: Scallop
350: Noddles
351: Comb
352: Dumpling
353: Oyster
354: Table Tennis paddle
355: Cosmetics Brush/Eyeliner Pencil
356: Chainsaw
357: Eraser
358: Lobster
359: Durian
360: Okra
361: Lipstick
362: Cosmetics Mirror
363: Curling
364: Table Tennis
# Download script/URL (optional) ---------------------------------------------------------------------------------------
download: |
from concurrent.futures import ThreadPoolExecutor
from pathlib import Path
import numpy as np
from ultralytics.utils import TQDM
from ultralytics.utils.checks import check_requirements
from ultralytics.utils.downloads import download
from ultralytics.utils.ops import xyxy2xywhn
check_requirements("faster-coco-eval")
from faster_coco_eval import COCO
# Train, Val Splits
dir = Path(yaml["path"])
for split, patches in [("train", 50 + 1), ("val", 43 + 1)]:
print(f"Processing {split} in {patches} patches ...")
images, labels = dir / "images" / split, dir / "labels" / split
images.mkdir(parents=True, exist_ok=True)
labels.mkdir(parents=True, exist_ok=True)
# Download
url = f"https://dorc.ks3-cn-beijing.ksyun.com/data-set/2020Objects365%E6%95%B0%E6%8D%AE%E9%9B%86/{split}/"
if split == "train":
download([f"{url}zhiyuan_objv2_{split}.tar.gz"], dir=dir) # annotations json
download([f"{url}patch{i}.tar.gz" for i in range(patches)], dir=images, threads=17) # 51 patches / 17 threads = 3
elif split == "val":
download([f"{url}zhiyuan_objv2_{split}.json"], dir=dir) # annotations json
download([f"{url}images/v1/patch{i}.tar.gz" for i in range(15 + 1)], dir=images, threads=16)
download([f"{url}images/v2/patch{i}.tar.gz" for i in range(16, patches)], dir=images, threads=16)
# Move
files = list(images.rglob("*.jpg"))
with ThreadPoolExecutor(max_workers=16) as executor:
list(TQDM(executor.map(lambda f: f.rename(images / f.name), files), total=len(files), desc=f"Moving {split} images"))
# Labels
coco = COCO(dir / f"zhiyuan_objv2_{split}.json")
names = [x["name"] for x in coco.loadCats(coco.getCatIds())]
for cid, cat in enumerate(names):
catIds = coco.getCatIds(catNms=[cat])
imgIds = coco.getImgIds(catIds=catIds)
def process_annotation(im):
"""Process and write annotations for a single image."""
try:
width, height = im["width"], im["height"]
path = Path(im["file_name"])
with open(labels / path.with_suffix(".txt").name, "a", encoding="utf-8") as file:
annIds = coco.getAnnIds(imgIds=im["id"], catIds=catIds, iscrowd=None)
for a in coco.loadAnns(annIds):
x, y, w, h = a["bbox"] # bounding box in xywh (xy top-left corner)
xyxy = np.array([x, y, x + w, y + h])[None] # pixels(1,4)
x, y, w, h = xyxy2xywhn(xyxy, w=width, h=height, clip=True)[0] # normalized and clipped
file.write(f"{cid} {x:.5f} {y:.5f} {w:.5f} {h:.5f}\n")
except Exception as e:
print(e)
images_list = coco.loadImgs(imgIds)
with ThreadPoolExecutor(max_workers=16) as executor:
list(TQDM(executor.map(process_annotation, images_list), total=len(images_list), desc=f"Class {cid + 1}/{len(names)} {cat}"))

58
ultralytics/cfg/datasets/SKU-110K.yaml Executable file
View File

@@ -0,0 +1,58 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# SKU-110K retail items dataset https://github.com/eg4000/SKU110K_CVPR19 by Trax Retail
# Documentation: https://docs.ultralytics.com/datasets/detect/sku-110k/
# Example usage: yolo train data=SKU-110K.yaml
# parent
# ├── ultralytics
# └── datasets
# └── SKU-110K ← downloads here (13.6 GB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: SKU-110K # dataset root dir
train: train.txt # train images (relative to 'path') 8219 images
val: val.txt # val images (relative to 'path') 588 images
test: test.txt # test images (optional) 2936 images
# Classes
names:
0: object
# Download script/URL (optional) ---------------------------------------------------------------------------------------
download: |
import shutil
from pathlib import Path
import numpy as np
import polars as pl
from ultralytics.utils import TQDM
from ultralytics.utils.downloads import download
from ultralytics.utils.ops import xyxy2xywh
# Download
dir = Path(yaml["path"]) # dataset root dir
parent = Path(dir.parent) # download dir
urls = ["http://trax-geometry.s3.amazonaws.com/cvpr_challenge/SKU110K_fixed.tar.gz"]
download(urls, dir=parent)
# Rename directories
if dir.exists():
shutil.rmtree(dir)
(parent / "SKU110K_fixed").rename(dir) # rename dir
(dir / "labels").mkdir(parents=True, exist_ok=True) # create labels dir
# Convert labels
names = "image", "x1", "y1", "x2", "y2", "class", "image_width", "image_height" # column names
for d in "annotations_train.csv", "annotations_val.csv", "annotations_test.csv":
x = pl.read_csv(dir / "annotations" / d, has_header=False, new_columns=names, infer_schema_length=None).to_numpy() # annotations
images, unique_images = x[:, 0], np.unique(x[:, 0])
with open((dir / d).with_suffix(".txt").__str__().replace("annotations_", ""), "w", encoding="utf-8") as f:
f.writelines(f"./images/{s}\n" for s in unique_images)
for im in TQDM(unique_images, desc=f"Converting {dir / d}"):
cls = 0 # single-class dataset
with open((dir / "labels" / im).with_suffix(".txt"), "a", encoding="utf-8") as f:
for r in x[images == im]:
w, h = r[6], r[7] # image width, height
xywh = xyxy2xywh(np.array([[r[1] / w, r[2] / h, r[3] / w, r[4] / h]]))[0] # instance
f.write(f"{cls} {xywh[0]:.5f} {xywh[1]:.5f} {xywh[2]:.5f} {xywh[3]:.5f}\n") # write label

346
ultralytics/cfg/datasets/TT100K.yaml Executable file
View File

@@ -0,0 +1,346 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Tsinghua-Tencent 100K (TT100K) dataset https://cg.cs.tsinghua.edu.cn/traffic-sign/ by Tsinghua University
# Documentation: https://cg.cs.tsinghua.edu.cn/traffic-sign/tutorial.html
# Paper: Traffic-Sign Detection and Classification in the Wild (CVPR 2016)
# License: CC BY-NC 2.0 license for non-commercial use only
# Example usage: yolo train data=TT100K.yaml
# parent
# ├── ultralytics
# └── datasets
# └── TT100K ← downloads here (~18 GB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: TT100K # dataset root dir
train: images/train # train images (relative to 'path') 6105 images
val: images/val # val images (relative to 'path') 7641 images (original 'other' split)
test: images/test # test images (relative to 'path') 3071 images
# Classes (221 traffic sign categories, 45 with sufficient training instances)
names:
0: pl5
1: pl10
2: pl15
3: pl20
4: pl25
5: pl30
6: pl40
7: pl50
8: pl60
9: pl70
10: pl80
11: pl90
12: pl100
13: pl110
14: pl120
15: pm5
16: pm10
17: pm13
18: pm15
19: pm20
20: pm25
21: pm30
22: pm35
23: pm40
24: pm46
25: pm50
26: pm55
27: pm8
28: pn
29: pne
30: ph4
31: ph4.5
32: ph5
33: ps
34: pg
35: ph1.5
36: ph2
37: ph2.1
38: ph2.2
39: ph2.4
40: ph2.5
41: ph2.8
42: ph2.9
43: ph3
44: ph3.2
45: ph3.5
46: ph3.8
47: ph4.2
48: ph4.3
49: ph4.8
50: ph5.3
51: ph5.5
52: pb
53: pr10
54: pr100
55: pr20
56: pr30
57: pr40
58: pr45
59: pr50
60: pr60
61: pr70
62: pr80
63: pr90
64: p1
65: p2
66: p3
67: p4
68: p5
69: p6
70: p7
71: p8
72: p9
73: p10
74: p11
75: p12
76: p13
77: p14
78: p15
79: p16
80: p17
81: p18
82: p19
83: p20
84: p21
85: p22
86: p23
87: p24
88: p25
89: p26
90: p27
91: p28
92: pa8
93: pa10
94: pa12
95: pa13
96: pa14
97: pb5
98: pc
99: pg
100: ph1
101: ph1.3
102: ph1.5
103: ph2
104: ph3
105: ph4
106: ph5
107: pi
108: pl0
109: pl4
110: pl5
111: pl8
112: pl10
113: pl15
114: pl20
115: pl25
116: pl30
117: pl35
118: pl40
119: pl50
120: pl60
121: pl65
122: pl70
123: pl80
124: pl90
125: pl100
126: pl110
127: pl120
128: pm2
129: pm8
130: pm10
131: pm13
132: pm15
133: pm20
134: pm25
135: pm30
136: pm35
137: pm40
138: pm46
139: pm50
140: pm55
141: pn
142: pne
143: po
144: pr10
145: pr100
146: pr20
147: pr30
148: pr40
149: pr45
150: pr50
151: pr60
152: pr70
153: pr80
154: ps
155: w1
156: w2
157: w3
158: w5
159: w8
160: w10
161: w12
162: w13
163: w16
164: w18
165: w20
166: w21
167: w22
168: w24
169: w28
170: w30
171: w31
172: w32
173: w34
174: w35
175: w37
176: w38
177: w41
178: w42
179: w43
180: w44
181: w45
182: w46
183: w47
184: w48
185: w49
186: w50
187: w51
188: w52
189: w53
190: w54
191: w55
192: w56
193: w57
194: w58
195: w59
196: w60
197: w62
198: w63
199: w66
200: i1
201: i2
202: i3
203: i4
204: i5
205: i6
206: i7
207: i8
208: i9
209: i10
210: i11
211: i12
212: i13
213: i14
214: i15
215: il60
216: il80
217: il100
218: il110
219: io
220: ip
# Download script/URL (optional) ---------------------------------------------------------------------------------------
download: |
import json
import shutil
from pathlib import Path
from PIL import Image
from ultralytics.utils import TQDM
from ultralytics.utils.downloads import download
def tt100k2yolo(dir):
"""Convert TT100K annotations to YOLO format with images/{split} and labels/{split} structure."""
data_dir = dir / "data"
anno_file = data_dir / "annotations.json"
print("Loading annotations...")
with open(anno_file, encoding="utf-8") as f:
data = json.load(f)
# Build class name to index mapping from yaml
names = yaml["names"]
class_to_idx = {v: k for k, v in names.items()}
# Create directories
for split in ["train", "val", "test"]:
(dir / "images" / split).mkdir(parents=True, exist_ok=True)
(dir / "labels" / split).mkdir(parents=True, exist_ok=True)
print("Converting annotations to YOLO format...")
skipped = 0
for img_id, img_data in TQDM(data["imgs"].items(), desc="Processing"):
img_path_str = img_data["path"]
if "train" in img_path_str:
split = "train"
elif "test" in img_path_str:
split = "test"
else:
split = "val"
# Source and destination paths
src_img = data_dir / img_path_str
if not src_img.exists():
continue
dst_img = dir / "images" / split / src_img.name
# Get image dimensions
try:
with Image.open(src_img) as img:
img_width, img_height = img.size
except Exception as e:
print(f"Error reading {src_img}: {e}")
continue
# Copy image to destination
shutil.copy2(src_img, dst_img)
# Convert annotations
label_file = dir / "labels" / split / f"{src_img.stem}.txt"
lines = []
for obj in img_data.get("objects", []):
category = obj["category"]
if category not in class_to_idx:
skipped += 1
continue
bbox = obj["bbox"]
xmin, ymin = bbox["xmin"], bbox["ymin"]
xmax, ymax = bbox["xmax"], bbox["ymax"]
# Convert to YOLO format (normalized center coordinates and dimensions)
x_center = ((xmin + xmax) / 2.0) / img_width
y_center = ((ymin + ymax) / 2.0) / img_height
width = (xmax - xmin) / img_width
height = (ymax - ymin) / img_height
# Clip to valid range
x_center = max(0, min(1, x_center))
y_center = max(0, min(1, y_center))
width = max(0, min(1, width))
height = max(0, min(1, height))
cls_idx = class_to_idx[category]
lines.append(f"{cls_idx} {x_center:.6f} {y_center:.6f} {width:.6f} {height:.6f}\n")
# Write label file
if lines:
label_file.write_text("".join(lines), encoding="utf-8")
if skipped:
print(f"Skipped {skipped} annotations with unknown categories")
print("Conversion complete!")
# Download
dir = Path(yaml["path"]) # dataset root dir
urls = ["https://cg.cs.tsinghua.edu.cn/traffic-sign/data_model_code/data.zip"]
download(urls, dir=dir, curl=True, threads=1)
# Convert
tt100k2yolo(dir)

102
ultralytics/cfg/datasets/VOC.yaml Executable file
View File

@@ -0,0 +1,102 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# PASCAL VOC dataset http://host.robots.ox.ac.uk/pascal/VOC by University of Oxford
# Documentation: https://docs.ultralytics.com/datasets/detect/voc/
# Example usage: yolo train data=VOC.yaml
# parent
# ├── ultralytics
# └── datasets
# └── VOC ← downloads here (2.8 GB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: VOC
train: # train images (relative to 'path') 16551 images
- images/train2012
- images/train2007
- images/val2012
- images/val2007
val: # val images (relative to 'path') 4952 images
- images/test2007
test: # test images (optional)
- images/test2007
# Classes
names:
0: aeroplane
1: bicycle
2: bird
3: boat
4: bottle
5: bus
6: car
7: cat
8: chair
9: cow
10: diningtable
11: dog
12: horse
13: motorbike
14: person
15: pottedplant
16: sheep
17: sofa
18: train
19: tvmonitor
# Download script/URL (optional) ---------------------------------------------------------------------------------------
download: |
import xml.etree.ElementTree as ET
from pathlib import Path
from ultralytics.utils.downloads import download
from ultralytics.utils import ASSETS_URL, TQDM
def convert_label(path, lb_path, year, image_id):
"""Converts XML annotations from VOC format to YOLO format by extracting bounding boxes and class IDs."""
def convert_box(size, box):
dw, dh = 1.0 / size[0], 1.0 / size[1]
x, y, w, h = (box[0] + box[1]) / 2.0 - 1, (box[2] + box[3]) / 2.0 - 1, box[1] - box[0], box[3] - box[2]
return x * dw, y * dh, w * dw, h * dh
with open(path / f"VOC{year}/Annotations/{image_id}.xml") as in_file, open(lb_path, "w", encoding="utf-8") as out_file:
tree = ET.parse(in_file)
root = tree.getroot()
size = root.find("size")
w = int(size.find("width").text)
h = int(size.find("height").text)
names = list(yaml["names"].values()) # names list
for obj in root.iter("object"):
cls = obj.find("name").text
if cls in names and int(obj.find("difficult").text) != 1:
xmlbox = obj.find("bndbox")
bb = convert_box((w, h), [float(xmlbox.find(x).text) for x in ("xmin", "xmax", "ymin", "ymax")])
cls_id = names.index(cls) # class id
out_file.write(" ".join(str(a) for a in (cls_id, *bb)) + "\n")
# Download
dir = Path(yaml["path"]) # dataset root dir
urls = [
f"{ASSETS_URL}/VOCtrainval_06-Nov-2007.zip", # 446MB, 5012 images
f"{ASSETS_URL}/VOCtest_06-Nov-2007.zip", # 438MB, 4953 images
f"{ASSETS_URL}/VOCtrainval_11-May-2012.zip", # 1.95GB, 17126 images
]
download(urls, dir=dir / "images", threads=3, exist_ok=True) # download and unzip over existing (required)
# Convert
path = dir / "images/VOCdevkit"
for year, image_set in ("2012", "train"), ("2012", "val"), ("2007", "train"), ("2007", "val"), ("2007", "test"):
imgs_path = dir / "images" / f"{image_set}{year}"
lbs_path = dir / "labels" / f"{image_set}{year}"
imgs_path.mkdir(exist_ok=True, parents=True)
lbs_path.mkdir(exist_ok=True, parents=True)
with open(path / f"VOC{year}/ImageSets/Main/{image_set}.txt") as f:
image_ids = f.read().strip().split()
for id in TQDM(image_ids, desc=f"{image_set}{year}"):
f = path / f"VOC{year}/JPEGImages/{id}.jpg" # old img path
lb_path = (lbs_path / f.name).with_suffix(".txt") # new label path
f.rename(imgs_path / f.name) # move image
convert_label(path, lb_path, year, id) # convert labels to YOLO format

87
ultralytics/cfg/datasets/VisDrone.yaml Executable file
View File

@@ -0,0 +1,87 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# VisDrone2019-DET dataset https://github.com/VisDrone/VisDrone-Dataset by Tianjin University
# Documentation: https://docs.ultralytics.com/datasets/detect/visdrone/
# Example usage: yolo train data=VisDrone.yaml
# parent
# ├── ultralytics
# └── datasets
# └── VisDrone ← downloads here (2.3 GB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: VisDrone # dataset root dir
train: images/train # train images (relative to 'path') 6471 images
val: images/val # val images (relative to 'path') 548 images
test: images/test # test-dev images (optional) 1610 images
# Classes
names:
0: pedestrian
1: people
2: bicycle
3: car
4: van
5: truck
6: tricycle
7: awning-tricycle
8: bus
9: motor
# Download script/URL (optional) ---------------------------------------------------------------------------------------
download: |
import os
from pathlib import Path
import shutil
from ultralytics.utils.downloads import download
from ultralytics.utils import ASSETS_URL, TQDM
def visdrone2yolo(dir, split, source_name=None):
"""Convert VisDrone annotations to YOLO format with images/{split} and labels/{split} structure."""
from PIL import Image
source_dir = dir / (source_name or f"VisDrone2019-DET-{split}")
images_dir = dir / "images" / split
labels_dir = dir / "labels" / split
labels_dir.mkdir(parents=True, exist_ok=True)
# Move images to new structure
if (source_images_dir := source_dir / "images").exists():
images_dir.mkdir(parents=True, exist_ok=True)
for img in source_images_dir.glob("*.jpg"):
img.rename(images_dir / img.name)
for f in TQDM((source_dir / "annotations").glob("*.txt"), desc=f"Converting {split}"):
img_size = Image.open(images_dir / f.with_suffix(".jpg").name).size
dw, dh = 1.0 / img_size[0], 1.0 / img_size[1]
lines = []
with open(f, encoding="utf-8") as file:
for row in [x.split(",") for x in file.read().strip().splitlines()]:
if row[4] != "0": # Skip ignored regions
x, y, w, h = map(int, row[:4])
cls = int(row[5]) - 1
# Convert to YOLO format
x_center, y_center = (x + w / 2) * dw, (y + h / 2) * dh
w_norm, h_norm = w * dw, h * dh
lines.append(f"{cls} {x_center:.6f} {y_center:.6f} {w_norm:.6f} {h_norm:.6f}\n")
(labels_dir / f.name).write_text("".join(lines), encoding="utf-8")
# Download (ignores test-challenge split)
dir = Path(yaml["path"]) # dataset root dir
urls = [
f"{ASSETS_URL}/VisDrone2019-DET-train.zip",
f"{ASSETS_URL}/VisDrone2019-DET-val.zip",
f"{ASSETS_URL}/VisDrone2019-DET-test-dev.zip",
# f"{ASSETS_URL}/VisDrone2019-DET-test-challenge.zip",
]
download(urls, dir=dir, threads=4)
# Convert
splits = {"VisDrone2019-DET-train": "train", "VisDrone2019-DET-val": "val", "VisDrone2019-DET-test-dev": "test"}
for folder, split in splits.items():
visdrone2yolo(dir, split, folder) # convert VisDrone annotations to YOLO labels
shutil.rmtree(dir / folder) # cleanup original directory

25
ultralytics/cfg/datasets/african-wildlife.yaml Executable file
View File

@@ -0,0 +1,25 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# African Wildlife dataset by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/detect/african-wildlife/
# Example usage: yolo train data=african-wildlife.yaml
# parent
# ├── ultralytics
# └── datasets
# └── african-wildlife ← downloads here (100 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: african-wildlife # dataset root dir
train: images/train # train images (relative to 'path') 1052 images
val: images/val # val images (relative to 'path') 225 images
test: images/test # test images (relative to 'path') 227 images
# Classes
names:
0: buffalo
1: elephant
2: rhino
3: zebra
# Download script/URL (optional)
download: https://github.com/ultralytics/assets/releases/download/v0.0.0/african-wildlife.zip

22
ultralytics/cfg/datasets/brain-tumor.yaml Executable file
View File

@@ -0,0 +1,22 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Brain-tumor dataset by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/detect/brain-tumor/
# Example usage: yolo train data=brain-tumor.yaml
# parent
# ├── ultralytics
# └── datasets
# └── brain-tumor ← downloads here (4.21 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: brain-tumor # dataset root dir
train: images/train # train images (relative to 'path') 893 images
val: images/val # val images (relative to 'path') 223 images
# Classes
names:
0: negative
1: positive
# Download script/URL (optional)
download: https://github.com/ultralytics/assets/releases/download/v0.0.0/brain-tumor.zip

44
ultralytics/cfg/datasets/carparts-seg.yaml Executable file
View File

@@ -0,0 +1,44 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Carparts-seg dataset by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/segment/carparts-seg/
# Example usage: yolo train data=carparts-seg.yaml
# parent
# ├── ultralytics
# └── datasets
# └── carparts-seg ← downloads here (133 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: carparts-seg # dataset root dir
train: images/train # train images (relative to 'path') 3516 images
val: images/val # val images (relative to 'path') 276 images
test: images/test # test images (relative to 'path') 401 images
# Classes
names:
0: back_bumper
1: back_door
2: back_glass
3: back_left_door
4: back_left_light
5: back_light
6: back_right_door
7: back_right_light
8: front_bumper
9: front_door
10: front_glass
11: front_left_door
12: front_left_light
13: front_light
14: front_right_door
15: front_right_light
16: hood
17: left_mirror
18: object
19: right_mirror
20: tailgate
21: trunk
22: wheel
# Download script/URL (optional)
download: https://github.com/ultralytics/assets/releases/download/v0.0.0/carparts-seg.zip

64
ultralytics/cfg/datasets/coco-pose.yaml Executable file
View File

@@ -0,0 +1,64 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# COCO 2017 Keypoints dataset https://cocodataset.org by Microsoft
# Documentation: https://docs.ultralytics.com/datasets/pose/coco/
# Example usage: yolo train data=coco-pose.yaml
# parent
# ├── ultralytics
# └── datasets
# └── coco-pose ← downloads here (20.1 GB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: coco-pose # dataset root dir
train: train2017.txt # train images (relative to 'path') 56599 images
val: val2017.txt # val images (relative to 'path') 2346 images
test: test-dev2017.txt # 20288 of 40670 images, submit to https://codalab.lisn.upsaclay.fr/competitions/7403
# Keypoints
kpt_shape: [17, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
flip_idx: [0, 2, 1, 4, 3, 6, 5, 8, 7, 10, 9, 12, 11, 14, 13, 16, 15]
# Classes
names:
0: person
# Keypoint names per class
kpt_names:
0:
- nose
- left_eye
- right_eye
- left_ear
- right_ear
- left_shoulder
- right_shoulder
- left_elbow
- right_elbow
- left_wrist
- right_wrist
- left_hip
- right_hip
- left_knee
- right_knee
- left_ankle
- right_ankle
# Download script/URL (optional)
download: |
from pathlib import Path
from ultralytics.utils import ASSETS_URL
from ultralytics.utils.downloads import download
# Download labels
dir = Path(yaml["path"]) # dataset root dir
urls = [f"{ASSETS_URL}/coco2017labels-pose.zip"]
download(urls, dir=dir.parent)
# Download data
urls = [
"http://images.cocodataset.org/zips/train2017.zip", # 19G, 118k images
"http://images.cocodataset.org/zips/val2017.zip", # 1G, 5k images
"http://images.cocodataset.org/zips/test2017.zip", # 7G, 41k images (optional)
]
download(urls, dir=dir / "images", threads=3)

118
ultralytics/cfg/datasets/coco.yaml Executable file
View File

@@ -0,0 +1,118 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# COCO 2017 dataset https://cocodataset.org by Microsoft
# Documentation: https://docs.ultralytics.com/datasets/detect/coco/
# Example usage: yolo train data=coco.yaml
# parent
# ├── ultralytics
# └── datasets
# └── coco ← downloads here (20.1 GB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: coco # dataset root dir
train: train2017.txt # train images (relative to 'path') 118287 images
val: val2017.txt # val images (relative to 'path') 5000 images
test: test-dev2017.txt # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794
# Classes
names:
0: person
1: bicycle
2: car
3: motorcycle
4: airplane
5: bus
6: train
7: truck
8: boat
9: traffic light
10: fire hydrant
11: stop sign
12: parking meter
13: bench
14: bird
15: cat
16: dog
17: horse
18: sheep
19: cow
20: elephant
21: bear
22: zebra
23: giraffe
24: backpack
25: umbrella
26: handbag
27: tie
28: suitcase
29: frisbee
30: skis
31: snowboard
32: sports ball
33: kite
34: baseball bat
35: baseball glove
36: skateboard
37: surfboard
38: tennis racket
39: bottle
40: wine glass
41: cup
42: fork
43: knife
44: spoon
45: bowl
46: banana
47: apple
48: sandwich
49: orange
50: broccoli
51: carrot
52: hot dog
53: pizza
54: donut
55: cake
56: chair
57: couch
58: potted plant
59: bed
60: dining table
61: toilet
62: tv
63: laptop
64: mouse
65: remote
66: keyboard
67: cell phone
68: microwave
69: oven
70: toaster
71: sink
72: refrigerator
73: book
74: clock
75: vase
76: scissors
77: teddy bear
78: hair drier
79: toothbrush
# Download script/URL (optional)
download: |
from pathlib import Path
from ultralytics.utils import ASSETS_URL
from ultralytics.utils.downloads import download
# Download labels
segments = True # segment or box labels
dir = Path(yaml["path"]) # dataset root dir
urls = [ASSETS_URL + ("/coco2017labels-segments.zip" if segments else "/coco2017labels.zip")] # labels
download(urls, dir=dir.parent)
# Download data
urls = [
"http://images.cocodataset.org/zips/train2017.zip", # 19G, 118k images
"http://images.cocodataset.org/zips/val2017.zip", # 1G, 5k images
"http://images.cocodataset.org/zips/test2017.zip", # 7G, 41k images (optional)
]
download(urls, dir=dir / "images", threads=3)

101
ultralytics/cfg/datasets/coco12-formats.yaml Executable file
View File

@@ -0,0 +1,101 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# COCO12-Formats dataset (12 images testing all supported image formats) by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/detect/coco12-formats/
# Example usage: yolo train data=coco12-formats.yaml
# parent
# ├── ultralytics
# └── datasets
# └── coco12-formats ← downloads here (1 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: coco12-formats # dataset root dir
train: images/train # train images (relative to 'path') 6 images
val: images/val # val images (relative to 'path') 6 images
test: # test images (optional)
# Classes
names:
0: person
1: bicycle
2: car
3: motorcycle
4: airplane
5: bus
6: train
7: truck
8: boat
9: traffic light
10: fire hydrant
11: stop sign
12: parking meter
13: bench
14: bird
15: cat
16: dog
17: horse
18: sheep
19: cow
20: elephant
21: bear
22: zebra
23: giraffe
24: backpack
25: umbrella
26: handbag
27: tie
28: suitcase
29: frisbee
30: skis
31: snowboard
32: sports ball
33: kite
34: baseball bat
35: baseball glove
36: skateboard
37: surfboard
38: tennis racket
39: bottle
40: wine glass
41: cup
42: fork
43: knife
44: spoon
45: bowl
46: banana
47: apple
48: sandwich
49: orange
50: broccoli
51: carrot
52: hot dog
53: pizza
54: donut
55: cake
56: chair
57: couch
58: potted plant
59: bed
60: dining table
61: toilet
62: tv
63: laptop
64: mouse
65: remote
66: keyboard
67: cell phone
68: microwave
69: oven
70: toaster
71: sink
72: refrigerator
73: book
74: clock
75: vase
76: scissors
77: teddy bear
78: hair drier
79: toothbrush
# Download script/URL (optional)
download: https://github.com/ultralytics/assets/releases/download/v0.0.0/coco12-formats.zip

101
ultralytics/cfg/datasets/coco128-seg.yaml Executable file
View File

@@ -0,0 +1,101 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# COCO128-seg dataset https://www.kaggle.com/datasets/ultralytics/coco128 (first 128 images from COCO train2017) by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/segment/coco/
# Example usage: yolo train data=coco128-seg.yaml
# parent
# ├── ultralytics
# └── datasets
# └── coco128-seg ← downloads here (7 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: coco128-seg # dataset root dir
train: images/train2017 # train images (relative to 'path') 128 images
val: images/train2017 # val images (relative to 'path') 128 images
test: # test images (optional)
# Classes
names:
0: person
1: bicycle
2: car
3: motorcycle
4: airplane
5: bus
6: train
7: truck
8: boat
9: traffic light
10: fire hydrant
11: stop sign
12: parking meter
13: bench
14: bird
15: cat
16: dog
17: horse
18: sheep
19: cow
20: elephant
21: bear
22: zebra
23: giraffe
24: backpack
25: umbrella
26: handbag
27: tie
28: suitcase
29: frisbee
30: skis
31: snowboard
32: sports ball
33: kite
34: baseball bat
35: baseball glove
36: skateboard
37: surfboard
38: tennis racket
39: bottle
40: wine glass
41: cup
42: fork
43: knife
44: spoon
45: bowl
46: banana
47: apple
48: sandwich
49: orange
50: broccoli
51: carrot
52: hot dog
53: pizza
54: donut
55: cake
56: chair
57: couch
58: potted plant
59: bed
60: dining table
61: toilet
62: tv
63: laptop
64: mouse
65: remote
66: keyboard
67: cell phone
68: microwave
69: oven
70: toaster
71: sink
72: refrigerator
73: book
74: clock
75: vase
76: scissors
77: teddy bear
78: hair drier
79: toothbrush
# Download script/URL (optional)
download: https://github.com/ultralytics/assets/releases/download/v0.0.0/coco128-seg.zip

101
ultralytics/cfg/datasets/coco128.yaml Executable file
View File

@@ -0,0 +1,101 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# COCO128 dataset https://www.kaggle.com/datasets/ultralytics/coco128 (first 128 images from COCO train2017) by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/detect/coco/
# Example usage: yolo train data=coco128.yaml
# parent
# ├── ultralytics
# └── datasets
# └── coco128 ← downloads here (7 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: coco128 # dataset root dir
train: images/train2017 # train images (relative to 'path') 128 images
val: images/train2017 # val images (relative to 'path') 128 images
test: # test images (optional)
# Classes
names:
0: person
1: bicycle
2: car
3: motorcycle
4: airplane
5: bus
6: train
7: truck
8: boat
9: traffic light
10: fire hydrant
11: stop sign
12: parking meter
13: bench
14: bird
15: cat
16: dog
17: horse
18: sheep
19: cow
20: elephant
21: bear
22: zebra
23: giraffe
24: backpack
25: umbrella
26: handbag
27: tie
28: suitcase
29: frisbee
30: skis
31: snowboard
32: sports ball
33: kite
34: baseball bat
35: baseball glove
36: skateboard
37: surfboard
38: tennis racket
39: bottle
40: wine glass
41: cup
42: fork
43: knife
44: spoon
45: bowl
46: banana
47: apple
48: sandwich
49: orange
50: broccoli
51: carrot
52: hot dog
53: pizza
54: donut
55: cake
56: chair
57: couch
58: potted plant
59: bed
60: dining table
61: toilet
62: tv
63: laptop
64: mouse
65: remote
66: keyboard
67: cell phone
68: microwave
69: oven
70: toaster
71: sink
72: refrigerator
73: book
74: clock
75: vase
76: scissors
77: teddy bear
78: hair drier
79: toothbrush
# Download script/URL (optional)
download: https://github.com/ultralytics/assets/releases/download/v0.0.0/coco128.zip

103
ultralytics/cfg/datasets/coco8-grayscale.yaml Executable file
View File

@@ -0,0 +1,103 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# COCO8-Grayscale dataset (first 8 images from COCO train2017) by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/detect/coco8-grayscale/
# Example usage: yolo train data=coco8-grayscale.yaml
# parent
# ├── ultralytics
# └── datasets
# └── coco8-grayscale ← downloads here (1 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: coco8-grayscale # dataset root dir
train: images/train # train images (relative to 'path') 4 images
val: images/val # val images (relative to 'path') 4 images
test: # test images (optional)
channels: 1
# Classes
names:
0: person
1: bicycle
2: car
3: motorcycle
4: airplane
5: bus
6: train
7: truck
8: boat
9: traffic light
10: fire hydrant
11: stop sign
12: parking meter
13: bench
14: bird
15: cat
16: dog
17: horse
18: sheep
19: cow
20: elephant
21: bear
22: zebra
23: giraffe
24: backpack
25: umbrella
26: handbag
27: tie
28: suitcase
29: frisbee
30: skis
31: snowboard
32: sports ball
33: kite
34: baseball bat
35: baseball glove
36: skateboard
37: surfboard
38: tennis racket
39: bottle
40: wine glass
41: cup
42: fork
43: knife
44: spoon
45: bowl
46: banana
47: apple
48: sandwich
49: orange
50: broccoli
51: carrot
52: hot dog
53: pizza
54: donut
55: cake
56: chair
57: couch
58: potted plant
59: bed
60: dining table
61: toilet
62: tv
63: laptop
64: mouse
65: remote
66: keyboard
67: cell phone
68: microwave
69: oven
70: toaster
71: sink
72: refrigerator
73: book
74: clock
75: vase
76: scissors
77: teddy bear
78: hair drier
79: toothbrush
# Download script/URL (optional)
download: https://github.com/ultralytics/assets/releases/download/v0.0.0/coco8-grayscale.zip

104
ultralytics/cfg/datasets/coco8-multispectral.yaml Executable file
View File

@@ -0,0 +1,104 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# COCO8-Multispectral dataset (COCO8 images interpolated across 10 channels in the visual spectrum) by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/detect/coco8-multispectral/
# Example usage: yolo train data=coco8-multispectral.yaml
# parent
# ├── ultralytics
# └── datasets
# └── coco8-multispectral ← downloads here (20.2 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: coco8-multispectral # dataset root dir
train: images/train # train images (relative to 'path') 4 images
val: images/val # val images (relative to 'path') 4 images
test: # test images (optional)
# Number of multispectral image channels
channels: 10
# Classes
names:
0: person
1: bicycle
2: car
3: motorcycle
4: airplane
5: bus
6: train
7: truck
8: boat
9: traffic light
10: fire hydrant
11: stop sign
12: parking meter
13: bench
14: bird
15: cat
16: dog
17: horse
18: sheep
19: cow
20: elephant
21: bear
22: zebra
23: giraffe
24: backpack
25: umbrella
26: handbag
27: tie
28: suitcase
29: frisbee
30: skis
31: snowboard
32: sports ball
33: kite
34: baseball bat
35: baseball glove
36: skateboard
37: surfboard
38: tennis racket
39: bottle
40: wine glass
41: cup
42: fork
43: knife
44: spoon
45: bowl
46: banana
47: apple
48: sandwich
49: orange
50: broccoli
51: carrot
52: hot dog
53: pizza
54: donut
55: cake
56: chair
57: couch
58: potted plant
59: bed
60: dining table
61: toilet
62: tv
63: laptop
64: mouse
65: remote
66: keyboard
67: cell phone
68: microwave
69: oven
70: toaster
71: sink
72: refrigerator
73: book
74: clock
75: vase
76: scissors
77: teddy bear
78: hair drier
79: toothbrush
# Download script/URL (optional)
download: https://github.com/ultralytics/assets/releases/download/v0.0.0/coco8-multispectral.zip

47
ultralytics/cfg/datasets/coco8-pose.yaml Executable file
View File

@@ -0,0 +1,47 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# COCO8-pose dataset (first 8 images from COCO train2017) by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/pose/coco8-pose/
# Example usage: yolo train data=coco8-pose.yaml
# parent
# ├── ultralytics
# └── datasets
# └── coco8-pose ← downloads here (1 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: coco8-pose # dataset root dir
train: images/train # train images (relative to 'path') 4 images
val: images/val # val images (relative to 'path') 4 images
test: # test images (optional)
# Keypoints
kpt_shape: [17, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
flip_idx: [0, 2, 1, 4, 3, 6, 5, 8, 7, 10, 9, 12, 11, 14, 13, 16, 15]
# Classes
names:
0: person
# Keypoint names per class
kpt_names:
0:
- nose
- left_eye
- right_eye
- left_ear
- right_ear
- left_shoulder
- right_shoulder
- left_elbow
- right_elbow
- left_wrist
- right_wrist
- left_hip
- right_hip
- left_knee
- right_knee
- left_ankle
- right_ankle
# Download script/URL (optional)
download: https://github.com/ultralytics/assets/releases/download/v0.0.0/coco8-pose.zip

101
ultralytics/cfg/datasets/coco8-seg.yaml Executable file
View File

@@ -0,0 +1,101 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# COCO8-seg dataset (first 8 images from COCO train2017) by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/segment/coco8-seg/
# Example usage: yolo train data=coco8-seg.yaml
# parent
# ├── ultralytics
# └── datasets
# └── coco8-seg ← downloads here (1 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: coco8-seg # dataset root dir
train: images/train # train images (relative to 'path') 4 images
val: images/val # val images (relative to 'path') 4 images
test: # test images (optional)
# Classes
names:
0: person
1: bicycle
2: car
3: motorcycle
4: airplane
5: bus
6: train
7: truck
8: boat
9: traffic light
10: fire hydrant
11: stop sign
12: parking meter
13: bench
14: bird
15: cat
16: dog
17: horse
18: sheep
19: cow
20: elephant
21: bear
22: zebra
23: giraffe
24: backpack
25: umbrella
26: handbag
27: tie
28: suitcase
29: frisbee
30: skis
31: snowboard
32: sports ball
33: kite
34: baseball bat
35: baseball glove
36: skateboard
37: surfboard
38: tennis racket
39: bottle
40: wine glass
41: cup
42: fork
43: knife
44: spoon
45: bowl
46: banana
47: apple
48: sandwich
49: orange
50: broccoli
51: carrot
52: hot dog
53: pizza
54: donut
55: cake
56: chair
57: couch
58: potted plant
59: bed
60: dining table
61: toilet
62: tv
63: laptop
64: mouse
65: remote
66: keyboard
67: cell phone
68: microwave
69: oven
70: toaster
71: sink
72: refrigerator
73: book
74: clock
75: vase
76: scissors
77: teddy bear
78: hair drier
79: toothbrush
# Download script/URL (optional)
download: https://github.com/ultralytics/assets/releases/download/v0.0.0/coco8-seg.zip

101
ultralytics/cfg/datasets/coco8.yaml Executable file
View File

@@ -0,0 +1,101 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# COCO8 dataset (first 8 images from COCO train2017) by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/detect/coco8/
# Example usage: yolo train data=coco8.yaml
# parent
# ├── ultralytics
# └── datasets
# └── coco8 ← downloads here (1 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: coco8 # dataset root dir
train: images/train # train images (relative to 'path') 4 images
val: images/val # val images (relative to 'path') 4 images
test: # test images (optional)
# Classes
names:
0: person
1: bicycle
2: car
3: motorcycle
4: airplane
5: bus
6: train
7: truck
8: boat
9: traffic light
10: fire hydrant
11: stop sign
12: parking meter
13: bench
14: bird
15: cat
16: dog
17: horse
18: sheep
19: cow
20: elephant
21: bear
22: zebra
23: giraffe
24: backpack
25: umbrella
26: handbag
27: tie
28: suitcase
29: frisbee
30: skis
31: snowboard
32: sports ball
33: kite
34: baseball bat
35: baseball glove
36: skateboard
37: surfboard
38: tennis racket
39: bottle
40: wine glass
41: cup
42: fork
43: knife
44: spoon
45: bowl
46: banana
47: apple
48: sandwich
49: orange
50: broccoli
51: carrot
52: hot dog
53: pizza
54: donut
55: cake
56: chair
57: couch
58: potted plant
59: bed
60: dining table
61: toilet
62: tv
63: laptop
64: mouse
65: remote
66: keyboard
67: cell phone
68: microwave
69: oven
70: toaster
71: sink
72: refrigerator
73: book
74: clock
75: vase
76: scissors
77: teddy bear
78: hair drier
79: toothbrush
# Download script/URL (optional)
download: https://github.com/ultralytics/assets/releases/download/v0.0.0/coco8.zip

32
ultralytics/cfg/datasets/construction-ppe.yaml Executable file
View File

@@ -0,0 +1,32 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Construction-PPE dataset by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/detect/construction-ppe/
# Example usage: yolo train data=construction-ppe.yaml
# parent
# ├── ultralytics
# └── datasets
# └── construction-ppe ← downloads here (178.4 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: construction-ppe # dataset root dir
train: images/train # train images (relative to 'path') 1132 images
val: images/val # val images (relative to 'path') 143 images
test: images/test # test images (relative to 'path') 141 images
# Classes
names:
0: helmet
1: gloves
2: vest
3: boots
4: goggles
5: none
6: Person
7: no_helmet
8: no_goggle
9: no_gloves
10: no_boots
# Download script/URL (optional)
download: https://github.com/ultralytics/assets/releases/download/v0.0.0/construction-ppe.zip

22
ultralytics/cfg/datasets/crack-seg.yaml Executable file
View File

@@ -0,0 +1,22 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Crack-seg dataset by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/segment/crack-seg/
# Example usage: yolo train data=crack-seg.yaml
# parent
# ├── ultralytics
# └── datasets
# └── crack-seg ← downloads here (91.6 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: crack-seg # dataset root dir
train: images/train # train images (relative to 'path') 3717 images
val: images/val # val images (relative to 'path') 112 images
test: images/test # test images (relative to 'path') 200 images
# Classes
names:
0: crack
# Download script/URL (optional)
download: https://github.com/ultralytics/assets/releases/download/v0.0.0/crack-seg.zip

52
ultralytics/cfg/datasets/dog-pose.yaml Executable file
View File

@@ -0,0 +1,52 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Dogs dataset http://vision.stanford.edu/aditya86/ImageNetDogs/ by Stanford
# Documentation: https://docs.ultralytics.com/datasets/pose/dog-pose/
# Example usage: yolo train data=dog-pose.yaml
# parent
# ├── ultralytics
# └── datasets
# └── dog-pose ← downloads here (337 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: dog-pose # dataset root dir
train: images/train # train images (relative to 'path') 6773 images
val: images/val # val images (relative to 'path') 1703 images
# Keypoints
kpt_shape: [24, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
# Classes
names:
0: dog
# Keypoint names per class
kpt_names:
0:
- front_left_paw
- front_left_knee
- front_left_elbow
- rear_left_paw
- rear_left_knee
- rear_left_elbow
- front_right_paw
- front_right_knee
- front_right_elbow
- rear_right_paw
- rear_right_knee
- rear_right_elbow
- tail_start
- tail_end
- left_ear_base
- right_ear_base
- nose
- chin
- left_ear_tip
- right_ear_tip
- left_eye
- right_eye
- withers
- throat
# Download script/URL (optional)
download: https://github.com/ultralytics/assets/releases/download/v0.0.0/dog-pose.zip

38
ultralytics/cfg/datasets/dota8-multispectral.yaml Executable file
View File

@@ -0,0 +1,38 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# DOTA8-Multispectral dataset (DOTA8 interpolated across 10 channels in the visual spectrum) by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/obb/dota8/
# Example usage: yolo train model=yolov8n-obb.pt data=dota8-multispectral.yaml
# parent
# ├── ultralytics
# └── datasets
# └── dota8-multispectral ← downloads here (37.3 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: dota8-multispectral # dataset root dir
train: images/train # train images (relative to 'path') 4 images
val: images/val # val images (relative to 'path') 4 images
# Number of multispectral image channels
channels: 10
# Classes for DOTA 1.0
names:
0: plane
1: ship
2: storage tank
3: baseball diamond
4: tennis court
5: basketball court
6: ground track field
7: harbor
8: bridge
9: large vehicle
10: small vehicle
11: helicopter
12: roundabout
13: soccer ball field
14: swimming pool
# Download script/URL (optional)
download: https://github.com/ultralytics/assets/releases/download/v0.0.0/dota8-multispectral.zip

35
ultralytics/cfg/datasets/dota8.yaml Executable file
View File

@@ -0,0 +1,35 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# DOTA8 dataset (8 images from the DOTAv1 split) by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/obb/dota8/
# Example usage: yolo train model=yolov8n-obb.pt data=dota8.yaml
# parent
# ├── ultralytics
# └── datasets
# └── dota8 ← downloads here (1 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: dota8 # dataset root dir
train: images/train # train images (relative to 'path') 4 images
val: images/val # val images (relative to 'path') 4 images
# Classes for DOTA 1.0
names:
0: plane
1: ship
2: storage tank
3: baseball diamond
4: tennis court
5: basketball court
6: ground track field
7: harbor
8: bridge
9: large vehicle
10: small vehicle
11: helicopter
12: roundabout
13: soccer ball field
14: swimming pool
# Download script/URL (optional)
download: https://github.com/ultralytics/assets/releases/download/v0.0.0/dota8.zip

50
ultralytics/cfg/datasets/hand-keypoints.yaml Executable file
View File

@@ -0,0 +1,50 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Hand Keypoints dataset by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/pose/hand-keypoints/
# Example usage: yolo train data=hand-keypoints.yaml
# parent
# ├── ultralytics
# └── datasets
# └── hand-keypoints ← downloads here (369 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: hand-keypoints # dataset root dir
train: images/train # train images (relative to 'path') 18776 images
val: images/val # val images (relative to 'path') 7992 images
# Keypoints
kpt_shape: [21, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
flip_idx: [0, 1, 2, 4, 3, 10, 11, 12, 13, 14, 5, 6, 7, 8, 9, 15, 16, 17, 18, 19, 20]
# Classes
names:
0: hand
# Keypoint names per class
kpt_names:
0:
- wrist
- thumb_cmc
- thumb_mcp
- thumb_ip
- thumb_tip
- index_mcp
- index_pip
- index_dip
- index_tip
- middle_mcp
- middle_pip
- middle_dip
- middle_tip
- ring_mcp
- ring_pip
- ring_dip
- ring_tip
- pinky_mcp
- pinky_pip
- pinky_dip
- pinky_tip
# Download script/URL (optional)
download: https://github.com/ultralytics/assets/releases/download/v0.0.0/hand-keypoints.zip

27
ultralytics/cfg/datasets/kitti.yaml Executable file
View File

@@ -0,0 +1,27 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# KITTI dataset by Karlsruhe Institute of Technology and Toyota Technological Institute at Chicago
# Documentation: https://docs.ultralytics.com/datasets/detect/kitti/
# Example usage: yolo train data=kitti.yaml
# parent
# ├── ultralytics
# └── datasets
# └── kitti ← downloads here (390.5 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: kitti # dataset root dir
train: images/train # train images (relative to 'path') 5985 images
val: images/val # val images (relative to 'path') 1496 images
names:
0: car
1: van
2: truck
3: pedestrian
4: person_sitting
5: cyclist
6: tram
7: misc
# Download script/URL (optional)
download: https://github.com/ultralytics/assets/releases/download/v0.0.0/kitti.zip

1240
ultralytics/cfg/datasets/lvis.yaml Executable file
View File

File diff suppressed because it is too large Load Diff

21
ultralytics/cfg/datasets/medical-pills.yaml Executable file
View File

@@ -0,0 +1,21 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Medical-pills dataset by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/detect/medical-pills/
# Example usage: yolo train data=medical-pills.yaml
# parent
# ├── ultralytics
# └── datasets
# └── medical-pills ← downloads here (8.19 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: medical-pills # dataset root dir
train: images/train # train images (relative to 'path') 92 images
val: images/val # val images (relative to 'path') 23 images
# Classes
names:
0: pill
# Download script/URL (optional)
download: https://github.com/ultralytics/assets/releases/download/v0.0.0/medical-pills.zip

56
ultralytics/cfg/datasets/mono2d_ground.yaml Executable file
View File

@@ -0,0 +1,56 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ground 2D Detection Dataset for Mono3D
# Custom annotation format with difficulty scores and class mapping
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: /mnt/nfs/mono3d/ydong_data/Detection/Detection2D_20260427 # dataset root dir
train: /mnt/nfs/mono3d/ydong_data/Detection/Detection2D_20260427/train.txt # train images
val: /mnt/nfs/mono3d/ydong_data/Detection/Detection2D_20260427/val.txt # val images
test: # test images (optional)
# Class mapping: string class names to numeric IDs
# Format: class_name: class_id (allows easy merging, e.g., car: 0, van: 0)
class_map:
car: 0
suv: 1
pickup: 2
medium_car: 3
van: 4
bus: 5
truck: 6
tanker: 6
large_truck: 6
construction_vehicle: 6
special_vehicle: 7
unknown: 8
pedestrian: 9
bicyclist: 10
motorcyclist: 10
bicycle: 11
motorcycle: 11
tricycle: 12
tricyclist: 12
traffic_sign: 13
wheel: 14
plate: 15
face: 16
car_fake: 17
bicyclist_fake: 18
pedestrian_fake: 19
car_carrier: 6
platform_truck: 6
# Training parameters
min_wh: 8.0 # Keep boxes whose width or height is at least this many pixels
# Recommended: 2 * smallest_stride (2 * 8 = 16) for network detectability
# Color space of input images
use_yuv444: false # Convert YUV444 to BGR in dataloader (BT.601 full range)
# Label file format (7 columns):
# [class_name x_center y_center width height difficulty1 difficulty2]
# Difficulty-based loss weighting: difficulty_weights 设计上是给 0/1/2/3 难度目标配置权重的，但当前 Ground 2D 检测的 box/cls/dfl loss 没有实际按它加权；当前 difficulty 主要作为额外 difficulty 二分类监督使用
difficulty_weights: [1.0, 1.0, 0.7, 0.3]

84
ultralytics/cfg/datasets/mono3d_ground.yaml Executable file
View File

@@ -0,0 +1,84 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ground 3D Detection Dataset for Mono3D
# Joint 2D + 3D detection with fisheye camera support
# Label format: 19-col (complete_3d) or 51-col (face_3d) per object
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: /mnt/nfs/mono3d/xdzhu_data/Mono3d/Mono3d_4face_2m_g1m3/driving_png_20260202 # dataset root dir of images
train: /mnt/nfs/mono3d/xdzhu_data/Mono3d/Mono3d_4face_2m_g1m3/driving_png_20260320/train.txt # train GT list
val: /mnt/nfs/mono3d/xdzhu_data/Mono3d/Mono3d_4face_2m_g1m3/driving_png_20260320/val.txt # val GT list
test: # test images (optional)
# Class mapping: string class names to numeric IDs
# Format: class_name: class_id (allows easy merging, e.g., car: 0, van: 0)
class_map:
car: 0
suv: 1
pickup: 2
medium_car: 3
van: 4
bus: 5
truck: 6
tanker: 6
large_truck: 6
construction_vehicle: 6
special_vehicle: 7
unknown: 8
pedestrian: 9
bicyclist: 10
motorcyclist: 10
bicycle: 11
motorcycle: 11
tricycle: 12
tricyclist: 12
traffic_sign: 13
wheel: 14
plate: 15
face: 16
car_fake: 17
bicyclist_fake: 18
pedestrian_fake: 19
car_carrier: 6
platform_truck: 6
# Training parameters
min_wh: 8.0 # Keep boxes whose width or height is at least this many pixels
# Color space of input images
use_yuv444: false # Standard RGB/BGR images (not YUV444)
# Difficulty-based loss weighting:
difficulty_weights: [1.0, 1.0, 0.7, 0.3]
# 3D Detection parameters
# Class groups for 3D label parsing (by mapped class ID)
face_3d_classes: [0, 1, 2, 3, 4, 5, 6, 7, 8, 17] # vehicles with 4-face annotations (51-col labels)
complete_3d_classes: [9, 10, 11, 12, 18, 19] # pedestrian/bike with whole-box 3D only (19-col labels)
fake_3d_classes: [17, 18, 19] # fake classes with an additional dedicated 3D prediction head
# Camera
ori_img_size: [1920, 1080] # Original image size [width, height]
# ROI-specific presets resolved by train_mono3d.py via --roi=<name>
default_roi: roi0
roi_configs:
roi0:
roi: [1920, 880] # ROI size [width, height], crop from [w//2, vanishing_point_y] 保留整宽，只裁掉一部分上下区域，适合大视野。
virtual_fx: 537 # Target focal length x for virtual camera (pixels) 537 本身不是代码实时算出来的，是人为选定的目标焦距/归一化基准。一般来自目标输入尺寸、ROI 后典型焦距或历史模型设定
virtual_camera_prob: -1.0 # -1 = always use virtual_fx only, >0 = probability of virtual camera augmentation 不会走 virtual-camera 分支，只走普通 ROI crop + resize + depth normalize
crop_center_mode: cxvy # Crop center mode: cxvy = crop around image center x and vanishing point y
roi1:
roi: [768, 352] # ROI size [width, height], crop from [vanishing_point_x, vanishing_point_y]
virtual_fx: 537 # Target focal length x for virtual camera (pixels)
virtual_camera_prob: 0.5 # 有50% 概率走 virtual-camera 分支
virtual_camera_val_zoom: true # Enable virtual-camera random zoom during validation/TensorBoard while keeping crop center fixed
crop_center_mode: vxvy # Crop center mode: vxvy = crop around vanishing point x and vanishing point y
# 3D Normalization scales (for loss computation) 通常应来自离线统计，比如训练集 z 深度和尺寸的均值/尺度，或者沿用历史模型经验值 【1. 给 3D head 一个合理物理量先验； 2. 让 z、size loss 的量级更稳定； 3. 保持训练输出和 decode/可视化使用同一套尺度】
norm_scales_3d:
z3d_scale: 24.415 # z3d_norm = (z3d - z3d_offset) / z3d_scale 真实深度为39.937 米时，模型预测0， 真值每多预测24.415米，模型预测值+1
z3d_offset: 39.937
size_scale: 1.945 # size_norm = (size - size_offset) / size_scale 长度为3.78米时，模型预测0， 真值每多1.945米，模型预测值+1
size_offset: 3.780
yaw_scale: 1.5707963 # pi/2

663
ultralytics/cfg/datasets/open-images-v7.yaml Executable file
View File

@@ -0,0 +1,663 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Open Images v7 dataset https://storage.googleapis.com/openimages/web/index.html by Google
# Documentation: https://docs.ultralytics.com/datasets/detect/open-images-v7/
# Example usage: yolo train data=open-images-v7.yaml
# parent
# ├── ultralytics
# └── datasets
# └── open-images-v7 ← downloads here (561 GB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: open-images-v7 # dataset root dir
train: images/train # train images (relative to 'path') 1743042 images
val: images/val # val images (relative to 'path') 41620 images
test: # test images (optional)
# Classes
names:
0: Accordion
1: Adhesive tape
2: Aircraft
3: Airplane
4: Alarm clock
5: Alpaca
6: Ambulance
7: Animal
8: Ant
9: Antelope
10: Apple
11: Armadillo
12: Artichoke
13: Auto part
14: Axe
15: Backpack
16: Bagel
17: Baked goods
18: Balance beam
19: Ball
20: Balloon
21: Banana
22: Band-aid
23: Banjo
24: Barge
25: Barrel
26: Baseball bat
27: Baseball glove
28: Bat (Animal)
29: Bathroom accessory
30: Bathroom cabinet
31: Bathtub
32: Beaker
33: Bear
34: Bed
35: Bee
36: Beehive
37: Beer
38: Beetle
39: Bell pepper
40: Belt
41: Bench
42: Bicycle
43: Bicycle helmet
44: Bicycle wheel
45: Bidet
46: Billboard
47: Billiard table
48: Binoculars
49: Bird
50: Blender
51: Blue jay
52: Boat
53: Bomb
54: Book
55: Bookcase
56: Boot
57: Bottle
58: Bottle opener
59: Bow and arrow
60: Bowl
61: Bowling equipment
62: Box
63: Boy
64: Brassiere
65: Bread
66: Briefcase
67: Broccoli
68: Bronze sculpture
69: Brown bear
70: Building
71: Bull
72: Burrito
73: Bus
74: Bust
75: Butterfly
76: Cabbage
77: Cabinetry
78: Cake
79: Cake stand
80: Calculator
81: Camel
82: Camera
83: Can opener
84: Canary
85: Candle
86: Candy
87: Cannon
88: Canoe
89: Cantaloupe
90: Car
91: Carnivore
92: Carrot
93: Cart
94: Cassette deck
95: Castle
96: Cat
97: Cat furniture
98: Caterpillar
99: Cattle
100: Ceiling fan
101: Cello
102: Centipede
103: Chainsaw
104: Chair
105: Cheese
106: Cheetah
107: Chest of drawers
108: Chicken
109: Chime
110: Chisel
111: Chopsticks
112: Christmas tree
113: Clock
114: Closet
115: Clothing
116: Coat
117: Cocktail
118: Cocktail shaker
119: Coconut
120: Coffee
121: Coffee cup
122: Coffee table
123: Coffeemaker
124: Coin
125: Common fig
126: Common sunflower
127: Computer keyboard
128: Computer monitor
129: Computer mouse
130: Container
131: Convenience store
132: Cookie
133: Cooking spray
134: Corded phone
135: Cosmetics
136: Couch
137: Countertop
138: Cowboy hat
139: Crab
140: Cream
141: Cricket ball
142: Crocodile
143: Croissant
144: Crown
145: Crutch
146: Cucumber
147: Cupboard
148: Curtain
149: Cutting board
150: Dagger
151: Dairy Product
152: Deer
153: Desk
154: Dessert
155: Diaper
156: Dice
157: Digital clock
158: Dinosaur
159: Dishwasher
160: Dog
161: Dog bed
162: Doll
163: Dolphin
164: Door
165: Door handle
166: Donut
167: Dragonfly
168: Drawer
169: Dress
170: Drill (Tool)
171: Drink
172: Drinking straw
173: Drum
174: Duck
175: Dumbbell
176: Eagle
177: Earrings
178: Egg (Food)
179: Elephant
180: Envelope
181: Eraser
182: Face powder
183: Facial tissue holder
184: Falcon
185: Fashion accessory
186: Fast food
187: Fax
188: Fedora
189: Filing cabinet
190: Fire hydrant
191: Fireplace
192: Fish
193: Flag
194: Flashlight
195: Flower
196: Flowerpot
197: Flute
198: Flying disc
199: Food
200: Food processor
201: Football
202: Football helmet
203: Footwear
204: Fork
205: Fountain
206: Fox
207: French fries
208: French horn
209: Frog
210: Fruit
211: Frying pan
212: Furniture
213: Garden Asparagus
214: Gas stove
215: Giraffe
216: Girl
217: Glasses
218: Glove
219: Goat
220: Goggles
221: Goldfish
222: Golf ball
223: Golf cart
224: Gondola
225: Goose
226: Grape
227: Grapefruit
228: Grinder
229: Guacamole
230: Guitar
231: Hair dryer
232: Hair spray
233: Hamburger
234: Hammer
235: Hamster
236: Hand dryer
237: Handbag
238: Handgun
239: Harbor seal
240: Harmonica
241: Harp
242: Harpsichord
243: Hat
244: Headphones
245: Heater
246: Hedgehog
247: Helicopter
248: Helmet
249: High heels
250: Hiking equipment
251: Hippopotamus
252: Home appliance
253: Honeycomb
254: Horizontal bar
255: Horse
256: Hot dog
257: House
258: Houseplant
259: Human arm
260: Human beard
261: Human body
262: Human ear
263: Human eye
264: Human face
265: Human foot
266: Human hair
267: Human hand
268: Human head
269: Human leg
270: Human mouth
271: Human nose
272: Humidifier
273: Ice cream
274: Indoor rower
275: Infant bed
276: Insect
277: Invertebrate
278: Ipod
279: Isopod
280: Jacket
281: Jacuzzi
282: Jaguar (Animal)
283: Jeans
284: Jellyfish
285: Jet ski
286: Jug
287: Juice
288: Kangaroo
289: Kettle
290: Kitchen & dining room table
291: Kitchen appliance
292: Kitchen knife
293: Kitchen utensil
294: Kitchenware
295: Kite
296: Knife
297: Koala
298: Ladder
299: Ladle
300: Ladybug
301: Lamp
302: Land vehicle
303: Lantern
304: Laptop
305: Lavender (Plant)
306: Lemon
307: Leopard
308: Light bulb
309: Light switch
310: Lighthouse
311: Lily
312: Limousine
313: Lion
314: Lipstick
315: Lizard
316: Lobster
317: Loveseat
318: Luggage and bags
319: Lynx
320: Magpie
321: Mammal
322: Man
323: Mango
324: Maple
325: Maracas
326: Marine invertebrates
327: Marine mammal
328: Measuring cup
329: Mechanical fan
330: Medical equipment
331: Microphone
332: Microwave oven
333: Milk
334: Miniskirt
335: Mirror
336: Missile
337: Mixer
338: Mixing bowl
339: Mobile phone
340: Monkey
341: Moths and butterflies
342: Motorcycle
343: Mouse
344: Muffin
345: Mug
346: Mule
347: Mushroom
348: Musical instrument
349: Musical keyboard
350: Nail (Construction)
351: Necklace
352: Nightstand
353: Oboe
354: Office building
355: Office supplies
356: Orange
357: Organ (Musical Instrument)
358: Ostrich
359: Otter
360: Oven
361: Owl
362: Oyster
363: Paddle
364: Palm tree
365: Pancake
366: Panda
367: Paper cutter
368: Paper towel
369: Parachute
370: Parking meter
371: Parrot
372: Pasta
373: Pastry
374: Peach
375: Pear
376: Pen
377: Pencil case
378: Pencil sharpener
379: Penguin
380: Perfume
381: Person
382: Personal care
383: Personal flotation device
384: Piano
385: Picnic basket
386: Picture frame
387: Pig
388: Pillow
389: Pineapple
390: Pitcher (Container)
391: Pizza
392: Pizza cutter
393: Plant
394: Plastic bag
395: Plate
396: Platter
397: Plumbing fixture
398: Polar bear
399: Pomegranate
400: Popcorn
401: Porch
402: Porcupine
403: Poster
404: Potato
405: Power plugs and sockets
406: Pressure cooker
407: Pretzel
408: Printer
409: Pumpkin
410: Punching bag
411: Rabbit
412: Raccoon
413: Racket
414: Radish
415: Ratchet (Device)
416: Raven
417: Rays and skates
418: Red panda
419: Refrigerator
420: Remote control
421: Reptile
422: Rhinoceros
423: Rifle
424: Ring binder
425: Rocket
426: Roller skates
427: Rose
428: Rugby ball
429: Ruler
430: Salad
431: Salt and pepper shakers
432: Sandal
433: Sandwich
434: Saucer
435: Saxophone
436: Scale
437: Scarf
438: Scissors
439: Scoreboard
440: Scorpion
441: Screwdriver
442: Sculpture
443: Sea lion
444: Sea turtle
445: Seafood
446: Seahorse
447: Seat belt
448: Segway
449: Serving tray
450: Sewing machine
451: Shark
452: Sheep
453: Shelf
454: Shellfish
455: Shirt
456: Shorts
457: Shotgun
458: Shower
459: Shrimp
460: Sink
461: Skateboard
462: Ski
463: Skirt
464: Skull
465: Skunk
466: Skyscraper
467: Slow cooker
468: Snack
469: Snail
470: Snake
471: Snowboard
472: Snowman
473: Snowmobile
474: Snowplow
475: Soap dispenser
476: Sock
477: Sofa bed
478: Sombrero
479: Sparrow
480: Spatula
481: Spice rack
482: Spider
483: Spoon
484: Sports equipment
485: Sports uniform
486: Squash (Plant)
487: Squid
488: Squirrel
489: Stairs
490: Stapler
491: Starfish
492: Stationary bicycle
493: Stethoscope
494: Stool
495: Stop sign
496: Strawberry
497: Street light
498: Stretcher
499: Studio couch
500: Submarine
501: Submarine sandwich
502: Suit
503: Suitcase
504: Sun hat
505: Sunglasses
506: Surfboard
507: Sushi
508: Swan
509: Swim cap
510: Swimming pool
511: Swimwear
512: Sword
513: Syringe
514: Table
515: Table tennis racket
516: Tablet computer
517: Tableware
518: Taco
519: Tank
520: Tap
521: Tart
522: Taxi
523: Tea
524: Teapot
525: Teddy bear
526: Telephone
527: Television
528: Tennis ball
529: Tennis racket
530: Tent
531: Tiara
532: Tick
533: Tie
534: Tiger
535: Tin can
536: Tire
537: Toaster
538: Toilet
539: Toilet paper
540: Tomato
541: Tool
542: Toothbrush
543: Torch
544: Tortoise
545: Towel
546: Tower
547: Toy
548: Traffic light
549: Traffic sign
550: Train
551: Training bench
552: Treadmill
553: Tree
554: Tree house
555: Tripod
556: Trombone
557: Trousers
558: Truck
559: Trumpet
560: Turkey
561: Turtle
562: Umbrella
563: Unicycle
564: Van
565: Vase
566: Vegetable
567: Vehicle
568: Vehicle registration plate
569: Violin
570: Volleyball (Ball)
571: Waffle
572: Waffle iron
573: Wall clock
574: Wardrobe
575: Washing machine
576: Waste container
577: Watch
578: Watercraft
579: Watermelon
580: Weapon
581: Whale
582: Wheel
583: Wheelchair
584: Whisk
585: Whiteboard
586: Willow
587: Window
588: Window blind
589: Wine
590: Wine glass
591: Wine rack
592: Winter melon
593: Wok
594: Woman
595: Wood-burning stove
596: Woodpecker
597: Worm
598: Wrench
599: Zebra
600: Zucchini
# Download script/URL (optional) ---------------------------------------------------------------------------------------
download: |
import warnings
from ultralytics.utils import LOGGER, SETTINGS, Path
from ultralytics.utils.checks import check_requirements
check_requirements("fiftyone")
import fiftyone as fo
import fiftyone.zoo as foz
name = "open-images-v7"
fo.config.dataset_zoo_dir = Path(SETTINGS["datasets_dir"]) / "fiftyone" / name
fraction = 1.0 # fraction of full dataset to use
LOGGER.warning("Open Images V7 dataset requires at least **561 GB of free space. Starting download...")
for split in "train", "validation": # 1743042 train, 41620 val images
train = split == "train"
# Load Open Images dataset
dataset = foz.load_zoo_dataset(
name,
split=split,
label_types=["detections"],
max_samples=round((1743042 if train else 41620) * fraction),
)
# Define classes
if train:
classes = dataset.default_classes # all classes
# classes = dataset.distinct('ground_truth.detections.label') # only observed classes
# Export to YOLO format
with warnings.catch_warnings():
warnings.filterwarnings("ignore", category=UserWarning, module="fiftyone.utils.yolo")
dataset.export(
export_dir=str(Path(SETTINGS["datasets_dir"]) / name),
dataset_type=fo.types.YOLOv5Dataset,
label_field="ground_truth",
split="val" if split == "validation" else split,
classes=classes,
overwrite=train,
)

22
ultralytics/cfg/datasets/package-seg.yaml Executable file
View File

@@ -0,0 +1,22 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Package-seg dataset by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/segment/package-seg/
# Example usage: yolo train data=package-seg.yaml
# parent
# ├── ultralytics
# └── datasets
# └── package-seg ← downloads here (103 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: package-seg # dataset root dir
train: images/train # train images (relative to 'path') 1920 images
val: images/val # val images (relative to 'path') 89 images
test: images/test # test images (relative to 'path') 188 images
# Classes
names:
0: package
# Download script/URL (optional)
download: https://github.com/ultralytics/assets/releases/download/v0.0.0/package-seg.zip

21
ultralytics/cfg/datasets/signature.yaml Executable file
View File

@@ -0,0 +1,21 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Signature dataset by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/detect/signature/
# Example usage: yolo train data=signature.yaml
# parent
# ├── ultralytics
# └── datasets
# └── signature ← downloads here (11.3 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: signature # dataset root dir
train: images/train # train images (relative to 'path') 143 images
val: images/val # val images (relative to 'path') 35 images
# Classes
names:
0: signature
# Download script/URL (optional)
download: https://github.com/ultralytics/assets/releases/download/v0.0.0/signature.zip

41
ultralytics/cfg/datasets/tiger-pose.yaml Executable file
View File

@@ -0,0 +1,41 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Tiger Pose dataset by Ultralytics
# Documentation: https://docs.ultralytics.com/datasets/pose/tiger-pose/
# Example usage: yolo train data=tiger-pose.yaml
# parent
# ├── ultralytics
# └── datasets
# └── tiger-pose ← downloads here (49.8 MB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: tiger-pose # dataset root dir
train: images/train # train images (relative to 'path') 210 images
val: images/val # val images (relative to 'path') 53 images
# Keypoints
kpt_shape: [12, 2] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
flip_idx: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
# Classes
names:
0: tiger
# Keypoint names per class
kpt_names:
0:
- nose
- head
- withers
- tail_base
- right_hind_hock
- right_hind_paw
- left_hind_paw
- left_hind_hock
- right_front_wrist
- right_front_paw
- left_front_wrist
- left_front_paw
# Download script/URL (optional)
download: https://github.com/ultralytics/assets/releases/download/v0.0.0/tiger-pose.zip

155
ultralytics/cfg/datasets/xView.yaml Executable file
View File

@@ -0,0 +1,155 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# DIUx xView 2018 Challenge dataset https://challenge.xviewdataset.org by U.S. National Geospatial-Intelligence Agency (NGA)
# -------- Download and extract data manually to `datasets/xView` before running the train command. --------
# Documentation: https://docs.ultralytics.com/datasets/detect/xview/
# Example usage: yolo train data=xView.yaml
# parent
# ├── ultralytics
# └── datasets
# └── xView ← downloads here (20.7 GB)
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: xView # dataset root dir
train: images/autosplit_train.txt # train images (relative to 'path') 90% of 847 train images
val: images/autosplit_val.txt # val images (relative to 'path') 10% of 847 train images
# Classes
names:
0: Fixed-wing Aircraft
1: Small Aircraft
2: Cargo Plane
3: Helicopter
4: Passenger Vehicle
5: Small Car
6: Bus
7: Pickup Truck
8: Utility Truck
9: Truck
10: Cargo Truck
11: Truck w/Box
12: Truck Tractor
13: Trailer
14: Truck w/Flatbed
15: Truck w/Liquid
16: Crane Truck
17: Railway Vehicle
18: Passenger Car
19: Cargo Car
20: Flat Car
21: Tank car
22: Locomotive
23: Maritime Vessel
24: Motorboat
25: Sailboat
26: Tugboat
27: Barge
28: Fishing Vessel
29: Ferry
30: Yacht
31: Container Ship
32: Oil Tanker
33: Engineering Vehicle
34: Tower crane
35: Container Crane
36: Reach Stacker
37: Straddle Carrier
38: Mobile Crane
39: Dump Truck
40: Haul Truck
41: Scraper/Tractor
42: Front loader/Bulldozer
43: Excavator
44: Cement Mixer
45: Ground Grader
46: Hut/Tent
47: Shed
48: Building
49: Aircraft Hangar
50: Damaged Building
51: Facility
52: Construction Site
53: Vehicle Lot
54: Helipad
55: Storage Tank
56: Shipping container lot
57: Shipping Container
58: Pylon
59: Tower
# Download script/URL (optional) ---------------------------------------------------------------------------------------
download: |
import json
from pathlib import Path
import shutil
import numpy as np
from PIL import Image
from ultralytics.utils import TQDM
from ultralytics.data.split import autosplit
from ultralytics.utils.ops import xyxy2xywhn
def convert_labels(fname=Path("xView/xView_train.geojson")):
"""Convert xView GeoJSON labels to YOLO format (classes 0-59) and save them as text files."""
path = fname.parent
with open(fname, encoding="utf-8") as f:
print(f"Loading {fname}...")
data = json.load(f)
# Make dirs
labels = path / "labels" / "train"
shutil.rmtree(labels, ignore_errors=True)
labels.mkdir(parents=True, exist_ok=True)
# xView classes 11-94 to 0-59
xview_class2index = [-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 0, 1, 2, -1, 3, -1, 4, 5, 6, 7, 8, -1, 9, 10, 11,
12, 13, 14, 15, -1, -1, 16, 17, 18, 19, 20, 21, 22, -1, 23, 24, 25, -1, 26, 27, -1, 28, -1,
29, 30, 31, 32, 33, 34, 35, 36, 37, -1, 38, 39, 40, 41, 42, 43, 44, 45, -1, -1, -1, -1, 46,
47, 48, 49, -1, 50, 51, -1, 52, -1, -1, -1, 53, 54, -1, 55, -1, -1, 56, -1, 57, -1, 58, 59]
shapes = {}
for feature in TQDM(data["features"], desc=f"Converting {fname}"):
p = feature["properties"]
if p["bounds_imcoords"]:
image_id = p["image_id"]
image_file = path / "train_images" / image_id
if image_file.exists(): # 1395.tif missing
try:
box = np.array([int(num) for num in p["bounds_imcoords"].split(",")])
assert box.shape[0] == 4, f"incorrect box shape {box.shape[0]}"
cls = p["type_id"]
cls = xview_class2index[int(cls)] # xView class to 0-59
assert 59 >= cls >= 0, f"incorrect class index {cls}"
# Write YOLO label
if image_id not in shapes:
shapes[image_id] = Image.open(image_file).size
box = xyxy2xywhn(box[None].astype(float), w=shapes[image_id][0], h=shapes[image_id][1], clip=True)
with open((labels / image_id).with_suffix(".txt"), "a", encoding="utf-8") as f:
f.write(f"{cls} {' '.join(f'{x:.6f}' for x in box[0])}\n") # write label.txt
except Exception as e:
print(f"WARNING: skipping one label for {image_file}: {e}")
# Download manually from https://challenge.xviewdataset.org
dir = Path(yaml["path"]) # dataset root dir
# urls = [
# "https://d307kc0mrhucc3.cloudfront.net/train_labels.zip", # train labels
# "https://d307kc0mrhucc3.cloudfront.net/train_images.zip", # 15G, 847 train images
# "https://d307kc0mrhucc3.cloudfront.net/val_images.zip", # 5G, 282 val images (no labels)
# ]
# download(urls, dir=dir)
# Convert labels
convert_labels(dir / "xView_train.geojson")
# Move images
images = Path(dir / "images")
images.mkdir(parents=True, exist_ok=True)
Path(dir / "train_images").rename(dir / "images" / "train")
Path(dir / "val_images").rename(dir / "images" / "val")
# Split
autosplit(dir / "images" / "train")

145
ultralytics/cfg/default.yaml Executable file
View File

@@ -0,0 +1,145 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Global configuration YAML with settings and hyperparameters for YOLO training, validation, prediction and export
# For documentation see https://docs.ultralytics.com/usage/cfg/
task: detect # (str) YOLO task, i.e. detect, segment, classify, pose, obb
mode: train # (str) YOLO mode, i.e. train, val, predict, export, track, benchmark
# Train settings -------------------------------------------------------------------------------------------------------
model: # (str, optional) path to model file, i.e. yolov8n.pt or yolov8n.yaml
data: # (str, optional) path to data file, i.e. coco8.yaml
epochs: 100 # (int) number of epochs to train for
time: # (float, optional) max hours to train; overrides epochs if set
patience: 100 # (int) early stop after N epochs without val improvement
batch: 16 # (int | float) batch size as int (e.g. 16), or float 0.0–1.0 for AutoBatch fraction of GPU memory
imgsz: 640 # (int | list) train/val use int (square); predict/export may use [h,w]
save: True # (bool) save train checkpoints and predict results
save_period: -1 # (int) save checkpoint every N epochs; disabled if < 1
cache: False # (bool | str) cache images in RAM (True/'ram') or on 'disk' to speed dataloading; False disables
device: # (int | str | list) device: 0 or [0,1,2,3] for CUDA, 'cpu'/'mps', or -1/[-1,-1] to auto-select idle GPUs
workers: 8 # (int) dataloader workers (per RANK if DDP)
project: # (str, optional) project name for results root
name: # (str, optional) experiment name; results in 'project/name'
exist_ok: False # (bool) overwrite existing 'project/name' if True
pretrained: True # (bool | str) use pretrained weights (bool) or load weights from path (str)
optimizer: auto # (str) optimizer: SGD, MuSGD, Adam, Adamax, AdamW, NAdam, RAdam, RMSProp, or auto
verbose: True # (bool) print verbose logs during training/val
seed: 0 # (int) random seed for reproducibility
deterministic: True # (bool) enable deterministic ops; reproducible but may be slower
single_cls: False # (bool) treat all classes as a single class
rect: False # (bool) rectangular batches for train; rectangular batching for val when mode='val'
cos_lr: False # (bool) cosine learning rate scheduler
close_mosaic: 10 # (int) disable mosaic augmentation for final N epochs (0 to keep enabled)
resume: False # (bool) resume training from last checkpoint in the run dir
amp: False # (bool) Automatic Mixed Precision (AMP) training; True runs AMP capability check
fraction: 1.0 # (float) fraction of training dataset to use (1.0 = all)
profile: False # (bool) profile ONNX/TensorRT speeds during training for loggers
batch_timing: False # (bool) log averaged train-batch timing breakdowns and supported dataset profiling
batch_timing_iters: 50 # (int) number of batches to average before printing timing breakdowns
freeze: # (int | list, optional) freeze first N layers (int) or specific layer indices (list)
multi_scale: 0.0 # (float) multi-scale range as a fraction of imgsz; sizes are rounded to stride multiples
compile: False # (bool | str) enable torch.compile() backend='inductor'; True="default", False=off, or "default|reduce-overhead|max-autotune-no-cudagraphs"
# Segmentation
overlap_mask: True # (bool) merge instance masks into one mask during training (segment only)
mask_ratio: 4 # (int) mask downsample ratio (segment only)
# Classification
dropout: 0.0 # (float) dropout for classification head (classify only)
# Val/Test settings ----------------------------------------------------------------------------------------------------
val: True # (bool) run validation/testing during training
split: val # (str) dataset split to evaluate: 'val', 'test' or 'train'
save_json: False # (bool) save results to COCO JSON for external evaluation
conf: # (float, optional) confidence threshold; defaults: predict=0.25, val=0.001
iou: 0.7 # (float) IoU threshold used for NMS
max_det: 300 # (int) maximum number of detections per image
half: False # (bool) use half precision (FP16) if supported
dnn: False # (bool) use OpenCV DNN for ONNX inference
plots: True # (bool) save plots and images during train/val
end2end: # (bool, optional) whether to use end2end head (YOLO26, YOLOv10) for predict/val/export
roi_metrics_only: False # (bool) compute validation metrics using ROI samples only when camera_mode metadata is available
# Predict settings -----------------------------------------------------------------------------------------------------
source: # (str, optional) path/dir/URL/stream for images or videos; e.g. 'ultralytics/assets' or '0' for webcam
vid_stride: 1 # (int) read every Nth frame for video sources
stream_buffer: False # (bool) True buffers all frames; False keeps the most recent frame for low-latency streams
visualize: False # (bool) visualize model features (predict) or TP/FP/FN confusion (val)
visualize_conf: 0.25 # (float) confidence threshold for human-readable validation/TensorBoard prediction visualization
augment: False # (bool) apply test-time augmentation during prediction
agnostic_nms: False # (bool) class-agnostic NMS
classes: # (int | list[int], optional) filter by class id(s), e.g. 0 or [0,2,3]
retina_masks: False # (bool) use high-resolution segmentation masks (segment)
embed: # (list[int], optional) return feature embeddings from given layer indices
# Visualize settings ---------------------------------------------------------------------------------------------------
show: False # (bool) show images/videos in a window if supported
save_frames: False # (bool) save individual frames from video predictions
save_txt: False # (bool) save results as .txt files (xywh format)
save_conf: False # (bool) save confidence scores with results
save_crop: False # (bool) save cropped prediction regions to files
show_labels: True # (bool) draw class labels on images, e.g. 'person'
show_conf: True # (bool) draw confidence values on images, e.g. '0.99'
show_boxes: True # (bool) draw bounding boxes on images
line_width: # (int, optional) line width of boxes; auto-scales with image size if not set
# Export settings ------------------------------------------------------------------------------------------------------
format: torchscript # (str) target format, e.g. torchscript|onnx|openvino|engine|coreml|saved_model|pb|tflite|edgetpu|tfjs|paddle|mnn|ncnn|imx|rknn|executorch|axelera
keras: False # (bool) TF SavedModel only (format=saved_model); enable Keras layers during export
optimize: False # (bool) TorchScript only; apply mobile optimizations to the scripted model
int8: False # (bool) INT8/PTQ where supported (openvino, engine, coreml, tflite, tfjs, mnn, imx, axelera); needs calibration data/fraction
dynamic: False # (bool) dynamic shapes for torchscript, onnx, openvino, engine, coreml; enable variable image sizes
simplify: True # (bool) ONNX/engine only; run graph simplifier for cleaner ONNX before runtime conversion
opset: # (int, optional) ONNX/engine only; opset version for export; leave unset to use a tested default
workspace: # (float, optional) engine (TensorRT) only; workspace size in GiB, e.g. 4
nms: False # (bool) fuse NMS into exported model when backend supports; if True, conf/iou apply (agnostic_nms except coreml)
# Hyperparameters ------------------------------------------------------------------------------------------------------
lr0: 0.01 # (float) initial learning rate (SGD=1e-2, Adam/AdamW=1e-3)
lrf: 0.01 # (float) final LR fraction; final LR = lr0 * lrf
momentum: 0.937 # (float) SGD momentum or Adam beta1
weight_decay: 0.0005 # (float) weight decay (L2 regularization)
warmup_epochs: 3.0 # (float) warmup epochs (fractions allowed)
warmup_momentum: 0.8 # (float) initial momentum during warmup
warmup_bias_lr: 0.1 # (float) bias learning rate during warmup
e2e_o2m_start: 0.8 # (float) initial one-to-many loss weight for end-to-end heads; one-to-one uses 1 - this value
e2e_o2m_final: 0.1 # (float) final one-to-many loss weight after decay; one-to-one uses 1 - this value
e2e_o2m_decay_epochs: # (float, optional) epochs used to linearly decay one-to-many weight to e2e_o2m_final; defaults to epochs - 1
loss_3d_warmup_epochs: # (float, optional) epochs before enabling 3D loss; defaults to warmup_epochs when unset
loss_3d_ramp_epochs: 10.0 # (float) epochs used to ramp 3D loss weight from 0 to loss_3d_weight_max
loss_3d_weight_max: 0.1 # (float) maximum multiplier applied to the summed 3D loss terms
edge_aux_loss_gain: 1.0 # (float) gain for 3D visible-edge auxiliary loss; <=0 disables edge GT decoding and loss
face_visibility_score_thresh: 0.05 # (float) visible-face score threshold used by 3D face supervision and visible-face metrics
box: 7.5 # (float) box loss gain
cls: 0.5 # (float) classification loss gain
dfl: 1.5 # (float) distribution focal loss gain
pose: 12.0 # (float) pose loss gain (pose tasks)
kobj: 1.0 # (float) keypoint objectness loss gain (pose tasks)
rle: 1.0 # (float) rle loss gain (pose tasks)
angle: 1.0 # (float) oriented angle loss gain (obb tasks)
nbs: 64 # (int) nominal batch size used for loss normalization
hsv_h: 0.015 # (float) HSV hue augmentation fraction
hsv_s: 0.7 # (float) HSV saturation augmentation fraction
hsv_v: 0.4 # (float) HSV value (brightness) augmentation fraction
degrees: 0.0 # (float) rotation degrees (+/-)
translate: 0.1 # (float) translation fraction (+/-)
scale: 0.5 # (float) scale gain (+/-)
shear: 0.0 # (float) shear degrees (+/-)
perspective: 0.0 # (float) perspective fraction (0–0.001 typical)
flipud: 0.0 # (float) vertical flip probability
fliplr: 0.5 # (float) horizontal flip probability
bgr: 0.0 # (float) RGB↔BGR channel swap probability
mosaic: 1.0 # (float) mosaic augmentation probability
mixup: 0.0 # (float) MixUp augmentation probability
cutmix: 0.0 # (float) CutMix augmentation probability
copy_paste: 0.0 # (float) segmentation copy-paste probability
copy_paste_mode: flip # (str) copy-paste strategy for segmentation: flip or mixup
auto_augment: randaugment # (str) classification auto augmentation policy: randaugment, autoaugment, augmix
erasing: 0.4 # (float) random erasing probability for classification (0.0–1.0)
# Custom config.yaml ---------------------------------------------------------------------------------------------------
cfg: # (str, optional) path to a config.yaml that overrides defaults
# Tracker settings ------------------------------------------------------------------------------------------------------
tracker: botsort.yaml # (str) tracker config file: botsort.yaml or bytetrack.yaml

17
ultralytics/cfg/models/11/yolo11-cls-resnet18.yaml Executable file
View File

@@ -0,0 +1,17 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLO11-cls image classification model with ResNet18 backbone
# Model docs: https://docs.ultralytics.com/models/yolo11
# Task docs: https://docs.ultralytics.com/tasks/classify
# Parameters
nc: 1000 # number of classes
# ResNet18 backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, TorchVision, [512, resnet18, DEFAULT, True, 2]] # truncate two layers from the end
# YOLO11n head
head:
- [-1, 1, Classify, [nc]] # Classify

33
ultralytics/cfg/models/11/yolo11-cls.yaml Executable file
View File

@@ -0,0 +1,33 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLO11-cls image classification model
# Model docs: https://docs.ultralytics.com/models/yolo11
# Task docs: https://docs.ultralytics.com/tasks/classify
# Parameters
nc: 1000 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolo11n-cls.yaml' will call yolo11-cls.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.50, 0.25, 1024] # summary: 86 layers, 1633584 parameters, 1633584 gradients, 0.5 GFLOPs
s: [0.50, 0.50, 1024] # summary: 86 layers, 5545488 parameters, 5545488 gradients, 1.6 GFLOPs
m: [0.50, 1.00, 512] # summary: 106 layers, 10455696 parameters, 10455696 gradients, 5.0 GFLOPs
l: [1.00, 1.00, 512] # summary: 176 layers, 12937104 parameters, 12937104 gradients, 6.2 GFLOPs
x: [1.00, 1.50, 512] # summary: 176 layers, 28458544 parameters, 28458544 gradients, 13.7 GFLOPs
# YOLO11n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 2, C3k2, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 2, C3k2, [1024, True]]
- [-1, 2, C2PSA, [1024]] # 9
# YOLO11n head
head:
- [-1, 1, Classify, [nc]] # Classify

50
ultralytics/cfg/models/11/yolo11-obb.yaml Executable file
View File

@@ -0,0 +1,50 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLO11-obb Oriented Bounding Boxes (OBB) model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolo11
# Task docs: https://docs.ultralytics.com/tasks/obb
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolo11n-obb.yaml' will call yolo11-obb.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.50, 0.25, 1024] # summary: 196 layers, 2695747 parameters, 2695731 gradients, 6.9 GFLOPs
s: [0.50, 0.50, 1024] # summary: 196 layers, 9744931 parameters, 9744915 gradients, 22.7 GFLOPs
m: [0.50, 1.00, 512] # summary: 246 layers, 20963523 parameters, 20963507 gradients, 72.2 GFLOPs
l: [1.00, 1.00, 512] # summary: 372 layers, 26220995 parameters, 26220979 gradients, 91.3 GFLOPs
x: [1.00, 1.50, 512] # summary: 372 layers, 58875331 parameters, 58875315 gradients, 204.3 GFLOPs
# YOLO11n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 2, C3k2, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 2, C3k2, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
- [-1, 2, C2PSA, [1024]] # 10
# YOLO11n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 2, C3k2, [512, False]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 2, C3k2, [256, False]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, OBB, [nc, 1]] # OBB(P3, P4, P5)

51
ultralytics/cfg/models/11/yolo11-pose.yaml Executable file
View File

@@ -0,0 +1,51 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLO11-pose keypoints/pose estimation model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolo11
# Task docs: https://docs.ultralytics.com/tasks/pose
# Parameters
nc: 80 # number of classes
kpt_shape: [17, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
scales: # model compound scaling constants, i.e. 'model=yolo11n-pose.yaml' will call yolo11-pose.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.50, 0.25, 1024] # summary: 196 layers, 2908507 parameters, 2908491 gradients, 7.7 GFLOPs
s: [0.50, 0.50, 1024] # summary: 196 layers, 9948811 parameters, 9948795 gradients, 23.5 GFLOPs
m: [0.50, 1.00, 512] # summary: 246 layers, 20973273 parameters, 20973257 gradients, 72.3 GFLOPs
l: [1.00, 1.00, 512] # summary: 372 layers, 26230745 parameters, 26230729 gradients, 91.4 GFLOPs
x: [1.00, 1.50, 512] # summary: 372 layers, 58889881 parameters, 58889865 gradients, 204.3 GFLOPs
# YOLO11n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 2, C3k2, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 2, C3k2, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
- [-1, 2, C2PSA, [1024]] # 10
# YOLO11n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 2, C3k2, [512, False]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 2, C3k2, [256, False]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, Pose, [nc, kpt_shape]] # Pose(P3, P4, P5)

50
ultralytics/cfg/models/11/yolo11-seg.yaml Executable file
View File

@@ -0,0 +1,50 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLO11-seg instance segmentation model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolo11
# Task docs: https://docs.ultralytics.com/tasks/segment
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolo11n-seg.yaml' will call yolo11-seg.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.50, 0.25, 1024] # summary: 203 layers, 2876848 parameters, 2876832 gradients, 10.5 GFLOPs
s: [0.50, 0.50, 1024] # summary: 203 layers, 10113248 parameters, 10113232 gradients, 35.8 GFLOPs
m: [0.50, 1.00, 512] # summary: 253 layers, 22420896 parameters, 22420880 gradients, 123.9 GFLOPs
l: [1.00, 1.00, 512] # summary: 379 layers, 27678368 parameters, 27678352 gradients, 143.0 GFLOPs
x: [1.00, 1.50, 512] # summary: 379 layers, 62142656 parameters, 62142640 gradients, 320.2 GFLOPs
# YOLO11n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 2, C3k2, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 2, C3k2, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
- [-1, 2, C2PSA, [1024]] # 10
# YOLO11n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 2, C3k2, [512, False]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 2, C3k2, [256, False]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, Segment, [nc, 32, 256]] # Segment(P3, P4, P5)

50
ultralytics/cfg/models/11/yolo11.yaml Executable file
View File

@@ -0,0 +1,50 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLO11 object detection model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolo11
# Task docs: https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolo11n.yaml' will call yolo11.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.50, 0.25, 1024] # summary: 181 layers, 2624080 parameters, 2624064 gradients, 6.6 GFLOPs
s: [0.50, 0.50, 1024] # summary: 181 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPs
m: [0.50, 1.00, 512] # summary: 231 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPs
l: [1.00, 1.00, 512] # summary: 357 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPs
x: [1.00, 1.50, 512] # summary: 357 layers, 56966176 parameters, 56966160 gradients, 196.0 GFLOPs
# YOLO11n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 2, C3k2, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 2, C3k2, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
- [-1, 2, C2PSA, [1024]] # 10
# YOLO11n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 2, C3k2, [512, False]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 2, C3k2, [256, False]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)

48
ultralytics/cfg/models/11/yoloe-11-seg.yaml Executable file
View File

@@ -0,0 +1,48 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLOE-11-seg instance segmentation model. For usage examples, see https://docs.ultralytics.com/tasks/segment
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yoloe-11n-seg.yaml' will call yoloe-11-seg.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.50, 0.25, 1024] # summary: 355 layers, 2876848 parameters, 2876832 gradients, 10.5 GFLOPs
s: [0.50, 0.50, 1024] # summary: 355 layers, 10113248 parameters, 10113232 gradients, 35.8 GFLOPs
m: [0.50, 1.00, 512] # summary: 445 layers, 22420896 parameters, 22420880 gradients, 123.9 GFLOPs
l: [1.00, 1.00, 512] # summary: 667 layers, 27678368 parameters, 27678352 gradients, 143.0 GFLOPs
x: [1.00, 1.50, 512] # summary: 667 layers, 62142656 parameters, 62142640 gradients, 320.2 GFLOPs
# YOLO11n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 2, C3k2, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 2, C3k2, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
- [-1, 2, C2PSA, [1024]] # 10
# YOLO11n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 2, C3k2, [512, False]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 2, C3k2, [256, False]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, YOLOESegment, [nc, 32, 256, 512, True]] # YOLOESegment(P3, P4, P5)

48
ultralytics/cfg/models/11/yoloe-11.yaml Executable file
View File

@@ -0,0 +1,48 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLOE-11 object detection model with P3/8 - P5/32 outputs. For usage examples, see https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yoloe-11n.yaml' will call yoloe-11.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.50, 0.25, 1024] # summary: 319 layers, 2624080 parameters, 2624064 gradients, 6.6 GFLOPs
s: [0.50, 0.50, 1024] # summary: 319 layers, 9458752 parameters, 9458736 gradients, 21.7 GFLOPs
m: [0.50, 1.00, 512] # summary: 409 layers, 20114688 parameters, 20114672 gradients, 68.5 GFLOPs
l: [1.00, 1.00, 512] # summary: 631 layers, 25372160 parameters, 25372144 gradients, 87.6 GFLOPs
x: [1.00, 1.50, 512] # summary: 631 layers, 56966176 parameters, 56966160 gradients, 196.0 GFLOPs
# YOLO11n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 2, C3k2, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 2, C3k2, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
- [-1, 2, C2PSA, [1024]] # 10
# YOLO11n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 2, C3k2, [512, False]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 2, C3k2, [256, False]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 2, C3k2, [512, False]] # 19 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 2, C3k2, [1024, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, YOLOEDetect, [nc, 512, True]] # YOLOEDetect(P3, P4, P5)

32
ultralytics/cfg/models/12/yolo12-cls.yaml Executable file
View File

@@ -0,0 +1,32 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# YOLO12-cls image classification model
# Model docs: https://docs.ultralytics.com/models/yolo12
# Task docs: https://docs.ultralytics.com/tasks/classify
# Parameters
nc: 1000 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolo12n-cls.yaml' will call yolo12-cls.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.50, 0.25, 1024] # summary: 152 layers, 1,820,976 parameters, 1,820,976 gradients, 3.7 GFLOPs
s: [0.50, 0.50, 1024] # summary: 152 layers, 6,206,992 parameters, 6,206,992 gradients, 13.6 GFLOPs
m: [0.50, 1.00, 512] # summary: 172 layers, 12,083,088 parameters, 12,083,088 gradients, 44.2 GFLOPs
l: [1.00, 1.00, 512] # summary: 312 layers, 15,558,640 parameters, 15,558,640 gradients, 56.9 GFLOPs
x: [1.00, 1.50, 512] # summary: 312 layers, 34,172,592 parameters, 34,172,592 gradients, 126.5 GFLOPs
# YOLO12n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 4, A2C2f, [512, True, 4]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 4, A2C2f, [1024, True, 1]] # 8
# YOLO12n head
head:
- [-1, 1, Classify, [nc]] # Classify

48
ultralytics/cfg/models/12/yolo12-obb.yaml Executable file
View File

@@ -0,0 +1,48 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# YOLO12-obb Oriented Bounding Boxes (OBB) model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolo12
# Task docs: https://docs.ultralytics.com/tasks/obb
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolo12n-obb.yaml' will call yolo12-obb.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.50, 0.25, 1024] # summary: 287 layers, 2,673,955 parameters, 2,673,939 gradients, 6.9 GFLOPs
s: [0.50, 0.50, 1024] # summary: 287 layers, 9,570,275 parameters, 9,570,259 gradients, 22.7 GFLOPs
m: [0.50, 1.00, 512] # summary: 307 layers, 21,048,003 parameters, 21,047,987 gradients, 71.8 GFLOPs
l: [1.00, 1.00, 512] # summary: 503 layers, 27,299,619 parameters, 27,299,603 gradients, 93.4 GFLOPs
x: [1.00, 1.50, 512] # summary: 503 layers, 61,119,939 parameters, 61,119,923 gradients, 208.6 GFLOPs
# YOLO12n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 4, A2C2f, [512, True, 4]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 4, A2C2f, [1024, True, 1]] # 8
# YOLO12n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 2, A2C2f, [512, False, -1]] # 11
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 2, A2C2f, [256, False, -1]] # 14
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 11], 1, Concat, [1]] # cat head P4
- [-1, 2, A2C2f, [512, False, -1]] # 17
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 8], 1, Concat, [1]] # cat head P5
- [-1, 2, C3k2, [1024, True]] # 20 (P5/32-large)
- [[14, 17, 20], 1, OBB, [nc, 1]] # OBB(P3, P4, P5)

49
ultralytics/cfg/models/12/yolo12-pose.yaml Executable file
View File

@@ -0,0 +1,49 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# YOLO12-pose keypoints/pose estimation model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolo12
# Task docs: https://docs.ultralytics.com/tasks/pose
# Parameters
nc: 80 # number of classes
kpt_shape: [17, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
scales: # model compound scaling constants, i.e. 'model=yolo12n-pose.yaml' will call yolo12-pose.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.50, 0.25, 1024] # summary: 287 layers, 2,886,715 parameters, 2,886,699 gradients, 7.8 GFLOPs
s: [0.50, 0.50, 1024] # summary: 287 layers, 9,774,155 parameters, 9,774,139 gradients, 23.5 GFLOPs
m: [0.50, 1.00, 512] # summary: 307 layers, 21,057,753 parameters, 21,057,737 gradients, 71.8 GFLOPs
l: [1.00, 1.00, 512] # summary: 503 layers, 27,309,369 parameters, 27,309,353 gradients, 93.5 GFLOPs
x: [1.00, 1.50, 512] # summary: 503 layers, 61,134,489 parameters, 61,134,473 gradients, 208.7 GFLOPs
# YOLO12n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 4, A2C2f, [512, True, 4]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 4, A2C2f, [1024, True, 1]] # 8
# YOLO12n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 2, A2C2f, [512, False, -1]] # 11
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 2, A2C2f, [256, False, -1]] # 14
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 11], 1, Concat, [1]] # cat head P4
- [-1, 2, A2C2f, [512, False, -1]] # 17
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 8], 1, Concat, [1]] # cat head P5
- [-1, 2, C3k2, [1024, True]] # 20 (P5/32-large)
- [[14, 17, 20], 1, Pose, [nc, kpt_shape]] # Pose(P3, P4, P5)

48
ultralytics/cfg/models/12/yolo12-seg.yaml Executable file
View File

@@ -0,0 +1,48 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# YOLO12-seg instance segmentation model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolo12
# Task docs: https://docs.ultralytics.com/tasks/segment
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolo12n-seg.yaml' will call yolo12-seg.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.50, 0.25, 1024] # summary: 294 layers, 2,855,056 parameters, 2,855,040 gradients, 10.6 GFLOPs
s: [0.50, 0.50, 1024] # summary: 294 layers, 9,938,592 parameters, 9,938,576 gradients, 35.7 GFLOPs
m: [0.50, 1.00, 512] # summary: 314 layers, 22,505,376 parameters, 22,505,360 gradients, 123.5 GFLOPs
l: [1.00, 1.00, 512] # summary: 510 layers, 28,756,992 parameters, 28,756,976 gradients, 145.1 GFLOPs
x: [1.00, 1.50, 512] # summary: 510 layers, 64,387,264 parameters, 64,387,248 gradients, 324.6 GFLOPs
# YOLO12n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 4, A2C2f, [512, True, 4]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 4, A2C2f, [1024, True, 1]] # 8
# YOLO12n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 2, A2C2f, [512, False, -1]] # 11
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 2, A2C2f, [256, False, -1]] # 14
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 11], 1, Concat, [1]] # cat head P4
- [-1, 2, A2C2f, [512, False, -1]] # 17
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 8], 1, Concat, [1]] # cat head P5
- [-1, 2, C3k2, [1024, True]] # 20 (P5/32-large)
- [[14, 17, 20], 1, Segment, [nc, 32, 256]] # Segment(P3, P4, P5)

48
ultralytics/cfg/models/12/yolo12.yaml Executable file
View File

@@ -0,0 +1,48 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# YOLO12 object detection model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolo12
# Task docs: https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolo12n.yaml' will call yolo12.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.50, 0.25, 1024] # summary: 272 layers, 2,602,288 parameters, 2,602,272 gradients, 6.7 GFLOPs
s: [0.50, 0.50, 1024] # summary: 272 layers, 9,284,096 parameters, 9,284,080 gradients, 21.7 GFLOPs
m: [0.50, 1.00, 512] # summary: 292 layers, 20,199,168 parameters, 20,199,152 gradients, 68.1 GFLOPs
l: [1.00, 1.00, 512] # summary: 488 layers, 26,450,784 parameters, 26,450,768 gradients, 89.7 GFLOPs
x: [1.00, 1.50, 512] # summary: 488 layers, 59,210,784 parameters, 59,210,768 gradients, 200.3 GFLOPs
# YOLO12n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 4, A2C2f, [512, True, 4]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 4, A2C2f, [1024, True, 1]] # 8
# YOLO12n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 2, A2C2f, [512, False, -1]] # 11
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 2, A2C2f, [256, False, -1]] # 14
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 11], 1, Concat, [1]] # cat head P4
- [-1, 2, A2C2f, [512, False, -1]] # 17
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 8], 1, Concat, [1]] # cat head P5
- [-1, 2, C3k2, [1024, True]] # 20 (P5/32-large)
- [[14, 17, 20], 1, Detect, [nc]] # Detect(P3, P4, P5)

51
ultralytics/cfg/models/26/yolo26-3d.yaml Executable file
View File

@@ -0,0 +1,51 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLO26 3D detection model with P3/8 - P5/32 outputs
# Extends yolo26.yaml with Detect3D head for joint 2D+3D detection
# Parameters
nc: 80 # number of classes
end2end: True # whether to use end-to-end mode
reg_max: 1 # DFL bins
scales: # model compound scaling constants
# [depth, width, max_channels]
n: [0.50, 0.25, 1024]
s: [0.50, 0.50, 1024]
m: [0.50, 1.00, 512]
l: [1.00, 1.00, 512]
x: [1.00, 1.50, 512]
# YOLO26n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 2, C3k2, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 2, C3k2, [1024, True]]
- [-1, 1, SPPF, [1024, 5, 3, True]] # 9
- [-1, 2, C2PSA, [1024]] # 10
# YOLO26n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 2, C3k2, [512, True]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 2, C3k2, [256, True]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 2, C3k2, [512, True]] # 19 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 1, C3k2, [1024, True, 0.5, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, Detect3D, [nc]] # Detect3D(P3, P4, P5)

33
ultralytics/cfg/models/26/yolo26-cls.yaml Executable file
View File

@@ -0,0 +1,33 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLO26-cls image classification model
# Model docs: https://docs.ultralytics.com/models/yolo26
# Task docs: https://docs.ultralytics.com/tasks/classify
# Parameters
nc: 1000 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolo26n-cls.yaml' will call yolo26-cls.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.50, 0.25, 1024] # summary: 86 layers, 2,812,104 parameters, 2,812,104 gradients, 0.5 GFLOPs
s: [0.50, 0.50, 1024] # summary: 86 layers, 6,724,008 parameters, 6,724,008 gradients, 1.6 GFLOPs
m: [0.50, 1.00, 512] # summary: 106 layers, 11,634,216 parameters, 11,634,216 gradients, 5.0 GFLOPs
l: [1.00, 1.00, 512] # summary: 176 layers, 14,115,624 parameters, 14,115,624 gradients, 6.2 GFLOPs
x: [1.00, 1.50, 512] # summary: 176 layers, 29,637,064 parameters, 29,637,064 gradients, 13.7 GFLOPs
# YOLO26n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 2, C3k2, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 2, C3k2, [1024, True]]
- [-1, 2, C2PSA, [1024]] # 9
# YOLO26n head
head:
- [-1, 1, Classify, [nc]] # Classify

52
ultralytics/cfg/models/26/yolo26-obb.yaml Executable file
View File

@@ -0,0 +1,52 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLO26-obb Oriented Bounding Boxes (OBB) model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolo26
# Task docs: https://docs.ultralytics.com/tasks/obb
# Parameters
nc: 80 # number of classes
end2end: True # whether to use end-to-end mode
reg_max: 1 # DFL bins
scales: # model compound scaling constants, i.e. 'model=yolo26n-obb.yaml' will call yolo26-obb.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.50, 0.25, 1024] # summary: 291 layers, 2,715,614 parameters, 2,715,614 gradients, 16.9 GFLOPs
s: [0.50, 0.50, 1024] # summary: 291 layers, 10,582,142 parameters, 10,582,142 gradients, 63.5 GFLOPs
m: [0.50, 1.00, 512] # summary: 311 layers, 23,593,918 parameters, 23,593,918 gradients, 211.9 GFLOPs
l: [1.00, 1.00, 512] # summary: 423 layers, 27,997,374 parameters, 27,997,374 gradients, 259.0 GFLOPs
x: [1.00, 1.50, 512] # summary: 423 layers, 62,811,678 parameters, 62,811,678 gradients, 578.9 GFLOPs
# YOLO26n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 2, C3k2, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 2, C3k2, [1024, True]]
- [-1, 1, SPPF, [1024, 5, 3, True]] # 9
- [-1, 2, C2PSA, [1024]] # 10
# YOLO26n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 2, C3k2, [512, True]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 2, C3k2, [256, True]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 2, C3k2, [512, True]] # 19 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 1, C3k2, [1024, True, 0.5, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, OBB26, [nc, 1]] # OBB26(P3, P4, P5)

60
ultralytics/cfg/models/26/yolo26-p2.yaml Executable file
View File

@@ -0,0 +1,60 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLO26 object detection model with P2/4 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolo26
# Task docs: https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
end2end: True # whether to use end-to-end mode
reg_max: 1 # DFL bins
scales: # model compound scaling constants, i.e. 'model=yolo26n-p2.yaml' will call yolo26-p2.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.50, 0.25, 1024] # summary: 329 layers, 2,662,400 parameters, 2,662,400 gradients, 9.5 GFLOPs
s: [0.50, 0.50, 1024] # summary: 329 layers, 9,765,856 parameters, 9,765,856 gradients, 27.8 GFLOPs
m: [0.50, 1.00, 512] # summary: 349 layers, 21,144,288 parameters, 21,144,288 gradients, 91.4 GFLOPs
l: [1.00, 1.00, 512] # summary: 489 layers, 25,815,520 parameters, 25,815,520 gradients, 115.3 GFLOPs
x: [1.00, 1.50, 512] # summary: 489 layers, 57,935,232 parameters, 57,935,232 gradients, 256.9 GFLOPs
# YOLO26n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 2, C3k2, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 2, C3k2, [1024, True]]
- [-1, 1, SPPF, [1024, 5, 3, True]] # 9
- [-1, 2, C2PSA, [1024]] # 10
# YOLO26n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 2, C3k2, [512, True]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 2, C3k2, [256, True]] # 16 (P3/8-small)
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 2], 1, Concat, [1]] # cat backbone P2
- [-1, 2, C3k2, [128, True]] # 19 (P2/4-xsmall)
- [-1, 1, Conv, [128, 3, 2]]
- [[-1, 16], 1, Concat, [1]] # cat head P3
- [-1, 2, C3k2, [256, True]] # 22 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 2, C3k2, [512, True]] # 25 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 1, C3k2, [1024, True, 0.5, True]] # 28 (P5/32-large)
- [[19, 22, 25, 28], 1, Detect, [nc]] # Detect(P2, P3, P4, P5)

62
ultralytics/cfg/models/26/yolo26-p6.yaml Executable file
View File

@@ -0,0 +1,62 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLO26 object detection model with P3/8 - P6/64 outputs
# Model docs: https://docs.ultralytics.com/models/yolo26
# Task docs: https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
end2end: True # whether to use end-to-end mode
reg_max: 1 # DFL bins
scales: # model compound scaling constants, i.e. 'model=yolo26n-p6.yaml' will call yolo26-p6.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.50, 0.25, 1024] # summary: 349 layers, 4,063,872 parameters, 4,063,872 gradients, 6.0 GFLOPs
s: [0.50, 0.50, 1024] # summary: 349 layers, 15,876,448 parameters, 15,876,448 gradients, 22.3 GFLOPs
m: [0.50, 1.00, 512] # summary: 369 layers, 32,400,096 parameters, 32,400,096 gradients, 77.3 GFLOPs
l: [1.00, 1.00, 512] # summary: 523 layers, 39,365,600 parameters, 39,365,600 gradients, 97.0 GFLOPs
x: [1.00, 1.50, 512] # summary: 523 layers, 88,330,368 parameters, 88,330,368 gradients, 216.6 GFLOPs
# YOLO26n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 2, C3k2, [512, True]]
- [-1, 1, Conv, [768, 3, 2]] # 7-P5/32
- [-1, 2, C3k2, [768, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 9-P6/64
- [-1, 2, C3k2, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 11
- [-1, 2, C2PSA, [1024]] # 12
# YOLO26n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 8], 1, Concat, [1]] # cat backbone P5
- [-1, 2, C3k2, [768, True]] # 15
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 2, C3k2, [512, True]] # 18
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 2, C3k2, [256, True]] # 21 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 18], 1, Concat, [1]] # cat head P4
- [-1, 2, C3k2, [512, True]] # 24 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 15], 1, Concat, [1]] # cat head P5
- [-1, 2, C3k2, [768, True]] # 27 (P5/32-large)
- [-1, 1, Conv, [768, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P6
- [-1, 1, C3k2, [1024, True, 0.5, True]] # 30 (P6/64-large)
- [[21, 24, 27, 30], 1, Detect, [nc]] # Detect(P3, P4, P5, P6)

53
ultralytics/cfg/models/26/yolo26-pose.yaml Executable file
View File

@@ -0,0 +1,53 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLO26-pose keypoints/pose estimation model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolo26
# Task docs: https://docs.ultralytics.com/tasks/pose
# Parameters
nc: 80 # number of classes
end2end: True # whether to use end-to-end mode
reg_max: 1 # DFL bins
kpt_shape: [17, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
scales: # model compound scaling constants, i.e. 'model=yolo26n-pose.yaml' will call yolo26-pose.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.50, 0.25, 1024] # summary: 363 layers, 3,747,554 parameters, 3,747,554 gradients, 10.7 GFLOPs
s: [0.50, 0.50, 1024] # summary: 363 layers, 11,870,498 parameters, 11,870,498 gradients, 29.6 GFLOPs
m: [0.50, 1.00, 512] # summary: 383 layers, 24,344,482 parameters, 24,344,482 gradients, 85.9 GFLOPs
l: [1.00, 1.00, 512] # summary: 495 layers, 28,747,938 parameters, 28,747,938 gradients, 104.3 GFLOPs
x: [1.00, 1.50, 512] # summary: 495 layers, 62,914,350 parameters, 62,914,350 gradients, 226.3 GFLOPs
# YOLO26n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 2, C3k2, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 2, C3k2, [1024, True]]
- [-1, 1, SPPF, [1024, 5, 3, True]] # 9
- [-1, 2, C2PSA, [1024]] # 10
# YOLO26n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 2, C3k2, [512, True]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 2, C3k2, [256, True]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 2, C3k2, [512, True]] # 19 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 1, C3k2, [1024, True, 0.5, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, Pose26, [nc, kpt_shape]] # Pose26(P3, P4, P5)

52
ultralytics/cfg/models/26/yolo26-seg.yaml Executable file
View File

@@ -0,0 +1,52 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLO26-seg instance segmentation model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolo26
# Task docs: https://docs.ultralytics.com/tasks/segment
# Parameters
nc: 80 # number of classes
end2end: True # whether to use end-to-end mode
reg_max: 1 # DFL bins
scales: # model compound scaling constants, i.e. 'model=yolo26n-seg.yaml' will call yolo26-seg.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.50, 0.25, 1024] # summary: 309 layers, 3,126,280 parameters, 3,126,280 gradients, 10.5 GFLOPs
s: [0.50, 0.50, 1024] # summary: 309 layers, 11,505,800 parameters, 11,505,800 gradients, 37.4 GFLOPs
m: [0.50, 1.00, 512] # summary: 329 layers, 27,112,072 parameters, 27,112,072 gradients, 132.5 GFLOPs
l: [1.00, 1.00, 512] # summary: 441 layers, 31,515,528 parameters, 31,515,528 gradients, 150.9 GFLOPs
x: [1.00, 1.50, 512] # summary: 441 layers, 70,693,800 parameters, 70,693,800 gradients, 337.7 GFLOPs
# YOLO26n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 2, C3k2, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 2, C3k2, [1024, True]]
- [-1, 1, SPPF, [1024, 5, 3, True]] # 9
- [-1, 2, C2PSA, [1024]] # 10
# YOLO26n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 2, C3k2, [512, True]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 2, C3k2, [256, True]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 2, C3k2, [512, True]] # 19 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 1, C3k2, [1024, True, 0.5, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, Segment26, [nc, 32, 256]] # Segment26(P3, P4, P5)

52
ultralytics/cfg/models/26/yolo26.yaml Executable file
View File

@@ -0,0 +1,52 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLO26 object detection model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolo26
# Task docs: https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
end2end: True # whether to use end-to-end mode
reg_max: 1 # DFL bins
scales: # model compound scaling constants, i.e. 'model=yolo26n.yaml' will call yolo26.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.50, 0.25, 1024] # summary: 260 layers, 2,572,280 parameters, 2,572,280 gradients, 6.1 GFLOPs
s: [0.50, 0.50, 1024] # summary: 260 layers, 10,009,784 parameters, 10,009,784 gradients, 22.8 GFLOPs
m: [0.50, 1.00, 512] # summary: 280 layers, 21,896,248 parameters, 21,896,248 gradients, 75.4 GFLOPs
l: [1.00, 1.00, 512] # summary: 392 layers, 26,299,704 parameters, 26,299,704 gradients, 93.8 GFLOPs
x: [1.00, 1.50, 512] # summary: 392 layers, 58,993,368 parameters, 58,993,368 gradients, 209.5 GFLOPs
# YOLO26n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 2, C3k2, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 2, C3k2, [1024, True]]
- [-1, 1, SPPF, [1024, 5, 3, True]] # 9
- [-1, 2, C2PSA, [1024]] # 10
# YOLO26n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 2, C3k2, [512, True]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 2, C3k2, [256, True]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 2, C3k2, [512, True]] # 19 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 1, C3k2, [1024, True, 0.5, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, Detect, [nc]] # Detect(P3, P4, P5)

53
ultralytics/cfg/models/26/yoloe-26-seg.yaml Executable file
View File

@@ -0,0 +1,53 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLOE-26 open-vocabulary instance segmentation model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolo26
# Task docs: https://docs.ultralytics.com/tasks/segment
# Parameters
nc: 80 # number of classes
end2end: True # whether to use end-to-end mode
reg_max: 1 # DFL bins
text_model: mobileclip2:b
scales: # model compound scaling constants, i.e. 'model=yoloe-26n-seg.yaml' will call yoloe-26-seg.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.50, 0.25, 1024] # summary: 347 layers, 5,615,540 parameters, 5,615,540 gradients, 11.7 GFLOPs
s: [0.50, 0.50, 1024] # summary: 347 layers, 15,272,852 parameters, 15,272,852 gradients, 39.3 GFLOPs
m: [0.50, 1.00, 512] # summary: 367 layers, 34,922,132 parameters, 34,922,132 gradients, 136.3 GFLOPs
l: [1.00, 1.00, 512] # summary: 479 layers, 39,325,588 parameters, 39,325,588 gradients, 154.7 GFLOPs
x: [1.00, 1.50, 512] # summary: 479 layers, 85,397,684 parameters, 85,397,684 gradients, 343.3 GFLOPs
# YOLOE26n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 2, C3k2, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 2, C3k2, [1024, True]]
- [-1, 1, SPPF, [1024, 5, 3, True]] # 9
- [-1, 2, C2PSA, [1024]] # 10
# YOLOE26n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 2, C3k2, [512, True]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 2, C3k2, [256, True]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 2, C3k2, [512, True]] # 19 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 1, C3k2, [1024, True, 0.5, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, YOLOESegment26, [nc, 32, 256, 512, True]] # YOLOESegment26(P3, P4, P5)

53
ultralytics/cfg/models/26/yoloe-26.yaml Executable file
View File

@@ -0,0 +1,53 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLOE-26 open-vocabulary object detection model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolo26
# Task docs: https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
end2end: True # whether to use end-to-end mode
reg_max: 1 # DFL bins
text_model: mobileclip2:b
scales: # model compound scaling constants, i.e. 'model=yoloe-26n.yaml' will call yoloe-26.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.50, 0.25, 1024] # summary: 298 layers, 5,061,540 parameters, 5,061,540 gradients, 7.3 GFLOPs
s: [0.50, 0.50, 1024] # summary: 298 layers, 13,776,836 parameters, 13,776,836 gradients, 24.8 GFLOPs
m: [0.50, 1.00, 512] # summary: 318 layers, 29,706,308 parameters, 29,706,308 gradients, 79.2 GFLOPs
l: [1.00, 1.00, 512] # summary: 430 layers, 34,109,764 parameters, 34,109,764 gradients, 97.6 GFLOPs
x: [1.00, 1.50, 512] # summary: 430 layers, 73,697,252 parameters, 73,697,252 gradients, 215.2 GFLOPs
# YOLOE26n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 2, C3k2, [256, False, 0.25]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 2, C3k2, [512, False, 0.25]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 2, C3k2, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 2, C3k2, [1024, True]]
- [-1, 1, SPPF, [1024, 5, 3, True]] # 9
- [-1, 2, C2PSA, [1024]] # 10
# YOLOE26n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 2, C3k2, [512, True]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 2, C3k2, [256, True]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 2, C3k2, [512, True]] # 19 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 1, C3k2, [1024, True, 0.5, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, YOLOEDetect, [nc, 512, True]] # YOLOEDetect(P3, P4, P5)

66
ultralytics/cfg/models/README.md Executable file
View File

@@ -0,0 +1,66 @@
<a href="https://www.ultralytics.com/" target="_blank"><img src="https://raw.githubusercontent.com/ultralytics/assets/main/logo/Ultralytics_Logotype_Original.svg" width="320" alt="Ultralytics logo"></a>
# Ultralytics Model Configurations
Welcome to the [Ultralytics](https://www.ultralytics.com/) models configuration directory. This folder contains a collection of model configuration files (`*.yaml`) that define Ultralytics YOLO model architectures. These configurations are used across common [computer vision](https://www.ultralytics.com/glossary/computer-vision-cv) tasks such as [object detection](https://docs.ultralytics.com/tasks/detect/), [image segmentation](https://docs.ultralytics.com/tasks/segment/), pose estimation, oriented bounding boxes (OBB), and image classification.
Configurations are designed to run efficiently on a range of hardware, from standard [CPUs](https://en.wikipedia.org/wiki/Central_processing_unit) to modern [GPUs](https://www.ultralytics.com/glossary/gpu-graphics-processing-unit). Pick a base model that matches your constraints (latency, memory, and accuracy), then customize it as needed.
To get started, choose a `*.yaml` file (see the [YAML format](https://www.ultralytics.com/glossary/yaml)) and use it to [train](https://docs.ultralytics.com/modes/train/) or export your model. For more details, see the Ultralytics [Documentation](https://docs.ultralytics.com/) or open a question on [GitHub Issues](https://github.com/ultralytics/ultralytics/issues).
## 🚀 Usage
Model configuration files (`*.yaml`) can be used directly from the [Command Line Interface (CLI)](https://docs.ultralytics.com/usage/cli/) via the `yolo` command:
```bash
# Train a YOLO26n detection model using the coco8 dataset for 100 epochs
yolo task=detect mode=train model=yolo26n.yaml data=coco8.yaml epochs=100 imgsz=640
```
The same YAML files can be used from [Python](https://www.python.org/), with the same [configuration arguments](https://docs.ultralytics.com/usage/cfg/) as in the CLI:
```python
from ultralytics import YOLO
# Initialize a YOLO26n model from a YAML configuration file
# This creates a model architecture without loading pre-trained weights
model = YOLO("yolo26n.yaml")
# Alternatively, load a pre-trained YOLO26n model directly
# This loads both the architecture and the weights trained on COCO
# model = YOLO("yolo26n.pt")
# Display model information (architecture, layers, parameters, etc.)
model.info()
# Train the model using the COCO8 dataset (a small subset of COCO) for 100 epochs
results = model.train(data="coco8.yaml", epochs=100, imgsz=640)
# Run inference with the trained model on an image
results = model("path/to/image.jpg")
```
## 🏗️ Pre-trained Model Architectures
Ultralytics supports a variety of model architectures. Visit the [Ultralytics Models](https://docs.ultralytics.com/models/) documentation page for details and usage examples, including:
- [YOLO26](https://docs.ultralytics.com/models/yolo26/)
- [YOLO12](https://docs.ultralytics.com/models/yolo12/)
- [YOLO11](https://docs.ultralytics.com/models/yolo11/)
- [YOLOv10](https://docs.ultralytics.com/models/yolov10/)
- [YOLOv9](https://docs.ultralytics.com/models/yolov9/)
- [YOLOv8](https://docs.ultralytics.com/models/yolov8/)
- [YOLOv5](https://docs.ultralytics.com/models/yolov5/)
- [And more...](https://docs.ultralytics.com/models/)
You can easily use any of these models by loading their configuration files (`.yaml`) or their [pre-trained](https://docs.pytorch.org/tutorials/beginner/transfer_learning_tutorial.html) checkpoints (`.pt`).
## 🤝 Contribute New Models
Have you developed a novel YOLO variant, experimented with a unique architecture, or achieved state-of-the-art results through specific tuning? We encourage you to share your innovations with the community by contributing to our Models section! Contributions like new model configurations, architectural improvements, or performance optimizations are highly valuable and help enrich the Ultralytics ecosystem.
Sharing your work here allows others to benefit from your insights and expands the range of available model choices. It's an excellent way to showcase your expertise and make the Ultralytics YOLO platform even more versatile and powerful.
To contribute, review the [Contributing Guide](https://docs.ultralytics.com/help/contributing/) for instructions on submitting a [Pull Request (PR)](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/about-pull-requests).
Thank you for helping improve the Ultralytics model zoo.

53
ultralytics/cfg/models/rt-detr/rtdetr-l.yaml Executable file
View File

@@ -0,0 +1,53 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics RT-DETR-l hybrid object detection model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/rtdetr
# Task docs: https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=rtdetr-l.yaml' will call rtdetr-l.yaml with scale 'l'
# [depth, width, max_channels]
l: [1.00, 1.00, 1024]
backbone:
# [from, repeats, module, args]
- [-1, 1, HGStem, [32, 48]] # 0-P2/4
- [-1, 6, HGBlock, [48, 128, 3]] # stage 1
- [-1, 1, DWConv, [128, 3, 2, 1, False]] # 2-P3/8
- [-1, 6, HGBlock, [96, 512, 3]] # stage 2
- [-1, 1, DWConv, [512, 3, 2, 1, False]] # 4-P4/16
- [-1, 6, HGBlock, [192, 1024, 5, True, False]] # cm, c2, k, light, shortcut
- [-1, 6, HGBlock, [192, 1024, 5, True, True]]
- [-1, 6, HGBlock, [192, 1024, 5, True, True]] # stage 3
- [-1, 1, DWConv, [1024, 3, 2, 1, False]] # 8-P5/32
- [-1, 6, HGBlock, [384, 2048, 5, True, False]] # stage 4
head:
- [-1, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 10 input_proj.2
- [-1, 1, AIFI, [1024, 8]]
- [-1, 1, Conv, [256, 1, 1]] # 12, Y5, lateral_convs.0
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [7, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 14 input_proj.1
- [[-2, -1], 1, Concat, [1]]
- [-1, 3, RepC3, [256]] # 16, fpn_blocks.0
- [-1, 1, Conv, [256, 1, 1]] # 17, Y4, lateral_convs.1
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [3, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 19 input_proj.0
- [[-2, -1], 1, Concat, [1]] # cat backbone P4
- [-1, 3, RepC3, [256]] # X3 (21), fpn_blocks.1
- [-1, 1, Conv, [256, 3, 2]] # 22, downsample_convs.0
- [[-1, 17], 1, Concat, [1]] # cat Y4
- [-1, 3, RepC3, [256]] # F4 (24), pan_blocks.0
- [-1, 1, Conv, [256, 3, 2]] # 25, downsample_convs.1
- [[-1, 12], 1, Concat, [1]] # cat Y5
- [-1, 3, RepC3, [256]] # F5 (27), pan_blocks.1
- [[21, 24, 27], 1, RTDETRDecoder, [nc]] # RTDETRDecoder(P3, P4, P5)

45
ultralytics/cfg/models/rt-detr/rtdetr-resnet101.yaml Executable file
View File

@@ -0,0 +1,45 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics RT-DETR-ResNet101 hybrid object detection model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/rtdetr
# Task docs: https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=rtdetr-resnet101.yaml' will call rtdetr-resnet101.yaml with scale 'l'
# [depth, width, max_channels]
l: [1.00, 1.00, 1024]
backbone:
# [from, repeats, module, args]
- [-1, 1, ResNetLayer, [3, 64, 1, True, 1]] # 0
- [-1, 1, ResNetLayer, [64, 64, 1, False, 3]] # 1
- [-1, 1, ResNetLayer, [256, 128, 2, False, 4]] # 2
- [-1, 1, ResNetLayer, [512, 256, 2, False, 23]] # 3
- [-1, 1, ResNetLayer, [1024, 512, 2, False, 3]] # 4
head:
- [-1, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 5
- [-1, 1, AIFI, [1024, 8]]
- [-1, 1, Conv, [256, 1, 1]] # 7
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [3, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 9
- [[-2, -1], 1, Concat, [1]]
- [-1, 3, RepC3, [256]] # 11
- [-1, 1, Conv, [256, 1, 1]] # 12
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [2, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 14
- [[-2, -1], 1, Concat, [1]] # cat backbone P4
- [-1, 3, RepC3, [256]] # X3 (16), fpn_blocks.1
- [-1, 1, Conv, [256, 3, 2]] # 17, downsample_convs.0
- [[-1, 12], 1, Concat, [1]] # cat Y4
- [-1, 3, RepC3, [256]] # F4 (19), pan_blocks.0
- [-1, 1, Conv, [256, 3, 2]] # 20, downsample_convs.1
- [[-1, 7], 1, Concat, [1]] # cat Y5
- [-1, 3, RepC3, [256]] # F5 (22), pan_blocks.1
- [[16, 19, 22], 1, RTDETRDecoder, [nc]] # RTDETRDecoder(P3, P4, P5)

45
ultralytics/cfg/models/rt-detr/rtdetr-resnet50.yaml Executable file
View File

@@ -0,0 +1,45 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics RT-DETR-ResNet50 hybrid object detection model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/rtdetr
# Task docs: https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=rtdetr-resnet50.yaml' will call rtdetr-resnet50.yaml with scale 'l'
# [depth, width, max_channels]
l: [1.00, 1.00, 1024]
backbone:
# [from, repeats, module, args]
- [-1, 1, ResNetLayer, [3, 64, 1, True, 1]] # 0
- [-1, 1, ResNetLayer, [64, 64, 1, False, 3]] # 1
- [-1, 1, ResNetLayer, [256, 128, 2, False, 4]] # 2
- [-1, 1, ResNetLayer, [512, 256, 2, False, 6]] # 3
- [-1, 1, ResNetLayer, [1024, 512, 2, False, 3]] # 4
head:
- [-1, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 5
- [-1, 1, AIFI, [1024, 8]]
- [-1, 1, Conv, [256, 1, 1]] # 7
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [3, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 9
- [[-2, -1], 1, Concat, [1]]
- [-1, 3, RepC3, [256]] # 11
- [-1, 1, Conv, [256, 1, 1]] # 12
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [2, 1, Conv, [256, 1, 1, None, 1, 1, False]] # 14
- [[-2, -1], 1, Concat, [1]] # cat backbone P4
- [-1, 3, RepC3, [256]] # X3 (16), fpn_blocks.1
- [-1, 1, Conv, [256, 3, 2]] # 17, downsample_convs.0
- [[-1, 12], 1, Concat, [1]] # cat Y4
- [-1, 3, RepC3, [256]] # F4 (19), pan_blocks.0
- [-1, 1, Conv, [256, 3, 2]] # 20, downsample_convs.1
- [[-1, 7], 1, Concat, [1]] # cat Y5
- [-1, 3, RepC3, [256]] # F5 (22), pan_blocks.1
- [[16, 19, 22], 1, RTDETRDecoder, [nc]] # RTDETRDecoder(P3, P4, P5)

57
ultralytics/cfg/models/rt-detr/rtdetr-x.yaml Executable file
View File

@@ -0,0 +1,57 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics RT-DETR-x hybrid object detection model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/rtdetr
# Task docs: https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=rtdetr-x.yaml' will call rtdetr-x.yaml with scale 'x'
# [depth, width, max_channels]
x: [1.00, 1.00, 2048]
backbone:
# [from, repeats, module, args]
- [-1, 1, HGStem, [32, 64]] # 0-P2/4
- [-1, 6, HGBlock, [64, 128, 3]] # stage 1
- [-1, 1, DWConv, [128, 3, 2, 1, False]] # 2-P3/8
- [-1, 6, HGBlock, [128, 512, 3]]
- [-1, 6, HGBlock, [128, 512, 3, False, True]] # 4-stage 2
- [-1, 1, DWConv, [512, 3, 2, 1, False]] # 5-P4/16
- [-1, 6, HGBlock, [256, 1024, 5, True, False]] # cm, c2, k, light, shortcut
- [-1, 6, HGBlock, [256, 1024, 5, True, True]]
- [-1, 6, HGBlock, [256, 1024, 5, True, True]]
- [-1, 6, HGBlock, [256, 1024, 5, True, True]]
- [-1, 6, HGBlock, [256, 1024, 5, True, True]] # 10-stage 3
- [-1, 1, DWConv, [1024, 3, 2, 1, False]] # 11-P5/32
- [-1, 6, HGBlock, [512, 2048, 5, True, False]]
- [-1, 6, HGBlock, [512, 2048, 5, True, True]] # 13-stage 4
head:
- [-1, 1, Conv, [384, 1, 1, None, 1, 1, False]] # 14 input_proj.2
- [-1, 1, AIFI, [2048, 8]]
- [-1, 1, Conv, [384, 1, 1]] # 16, Y5, lateral_convs.0
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [10, 1, Conv, [384, 1, 1, None, 1, 1, False]] # 18 input_proj.1
- [[-2, -1], 1, Concat, [1]]
- [-1, 3, RepC3, [384]] # 20, fpn_blocks.0
- [-1, 1, Conv, [384, 1, 1]] # 21, Y4, lateral_convs.1
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [4, 1, Conv, [384, 1, 1, None, 1, 1, False]] # 23 input_proj.0
- [[-2, -1], 1, Concat, [1]] # cat backbone P4
- [-1, 3, RepC3, [384]] # X3 (25), fpn_blocks.1
- [-1, 1, Conv, [384, 3, 2]] # 26, downsample_convs.0
- [[-1, 21], 1, Concat, [1]] # cat Y4
- [-1, 3, RepC3, [384]] # F4 (28), pan_blocks.0
- [-1, 1, Conv, [384, 3, 2]] # 29, downsample_convs.1
- [[-1, 16], 1, Concat, [1]] # cat Y5
- [-1, 3, RepC3, [384]] # F5 (31), pan_blocks.1
- [[25, 28, 31], 1, RTDETRDecoder, [nc]] # RTDETRDecoder(P3, P4, P5)

45
ultralytics/cfg/models/v10/yolov10b.yaml Executable file
View File

@@ -0,0 +1,45 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# YOLOv10b object detection model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolov10
# Task docs: https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' uses the 'n' scale
# [depth, width, max_channels]
b: [0.67, 1.00, 512]
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, SCDown, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, SCDown, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2fCIB, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
- [-1, 1, PSA, [1024]] # 10
# YOLOv10 head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2fCIB, [512, True]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 3, C2fCIB, [512, True]] # 19 (P4/16-medium)
- [-1, 1, SCDown, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 3, C2fCIB, [1024, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, v10Detect, [nc]] # v10Detect(P3, P4, P5)

45
ultralytics/cfg/models/v10/yolov10l.yaml Executable file
View File

@@ -0,0 +1,45 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# YOLOv10l object detection model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolov10
# Task docs: https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' uses the 'n' scale
# [depth, width, max_channels]
l: [1.00, 1.00, 512]
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, SCDown, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, SCDown, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2fCIB, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
- [-1, 1, PSA, [1024]] # 10
# YOLOv10 head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2fCIB, [512, True]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 3, C2fCIB, [512, True]] # 19 (P4/16-medium)
- [-1, 1, SCDown, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 3, C2fCIB, [1024, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, v10Detect, [nc]] # v10Detect(P3, P4, P5)

45
ultralytics/cfg/models/v10/yolov10m.yaml Executable file
View File

@@ -0,0 +1,45 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# YOLOv10m object detection model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolov10
# Task docs: https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' uses the 'n' scale
# [depth, width, max_channels]
m: [0.67, 0.75, 768]
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, SCDown, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, SCDown, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2fCIB, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
- [-1, 1, PSA, [1024]] # 10
# YOLOv10 head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 3, C2fCIB, [512, True]] # 19 (P4/16-medium)
- [-1, 1, SCDown, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 3, C2fCIB, [1024, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, v10Detect, [nc]] # v10Detect(P3, P4, P5)

45
ultralytics/cfg/models/v10/yolov10n.yaml Executable file
View File

@@ -0,0 +1,45 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# YOLOv10n object detection model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolov10
# Task docs: https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' uses the 'n' scale
# [depth, width, max_channels]
n: [0.33, 0.25, 1024]
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, SCDown, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, SCDown, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
- [-1, 1, PSA, [1024]] # 10
# YOLOv10 head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 19 (P4/16-medium)
- [-1, 1, SCDown, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 3, C2fCIB, [1024, True, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, v10Detect, [nc]] # v10Detect(P3, P4, P5)

45
ultralytics/cfg/models/v10/yolov10s.yaml Executable file
View File

@@ -0,0 +1,45 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# YOLOv10s object detection model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolov10
# Task docs: https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' uses the 'n' scale
# [depth, width, max_channels]
s: [0.33, 0.50, 1024]
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, SCDown, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, SCDown, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2fCIB, [1024, True, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
- [-1, 1, PSA, [1024]] # 10
# YOLOv10 head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 19 (P4/16-medium)
- [-1, 1, SCDown, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 3, C2fCIB, [1024, True, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, v10Detect, [nc]] # v10Detect(P3, P4, P5)

45
ultralytics/cfg/models/v10/yolov10x.yaml Executable file
View File

@@ -0,0 +1,45 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# YOLOv10x object detection model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolov10
# Task docs: https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' uses the 'n' scale
# [depth, width, max_channels]
x: [1.00, 1.25, 512]
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, SCDown, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2fCIB, [512, True]]
- [-1, 1, SCDown, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2fCIB, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
- [-1, 1, PSA, [1024]] # 10
# YOLOv10 head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2fCIB, [512, True]] # 13
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 16 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 13], 1, Concat, [1]] # cat head P4
- [-1, 3, C2fCIB, [512, True]] # 19 (P4/16-medium)
- [-1, 1, SCDown, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 3, C2fCIB, [1024, True]] # 22 (P5/32-large)
- [[16, 19, 22], 1, v10Detect, [nc]] # v10Detect(P3, P4, P5)

49
ultralytics/cfg/models/v3/yolov3-spp.yaml Executable file
View File

@@ -0,0 +1,49 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLOv3-SPP object detection model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolov3
# Task docs: https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
depth_multiple: 1.0 # model depth multiple
width_multiple: 1.0 # layer channel multiple
# darknet53 backbone
backbone:
# [from, number, module, args]
- [-1, 1, Conv, [32, 3, 1]] # 0
- [-1, 1, Conv, [64, 3, 2]] # 1-P1/2
- [-1, 1, Bottleneck, [64]]
- [-1, 1, Conv, [128, 3, 2]] # 3-P2/4
- [-1, 2, Bottleneck, [128]]
- [-1, 1, Conv, [256, 3, 2]] # 5-P3/8
- [-1, 8, Bottleneck, [256]]
- [-1, 1, Conv, [512, 3, 2]] # 7-P4/16
- [-1, 8, Bottleneck, [512]]
- [-1, 1, Conv, [1024, 3, 2]] # 9-P5/32
- [-1, 4, Bottleneck, [1024]] # 10
# YOLOv3-SPP head
head:
- [-1, 1, Bottleneck, [1024, False]]
- [-1, 1, SPP, [512, [5, 9, 13]]]
- [-1, 1, Conv, [1024, 3, 1]]
- [-1, 1, Conv, [512, 1, 1]]
- [-1, 1, Conv, [1024, 3, 1]] # 15 (P5/32-large)
- [-2, 1, Conv, [256, 1, 1]]
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 8], 1, Concat, [1]] # cat backbone P4
- [-1, 1, Bottleneck, [512, False]]
- [-1, 1, Bottleneck, [512, False]]
- [-1, 1, Conv, [256, 1, 1]]
- [-1, 1, Conv, [512, 3, 1]] # 22 (P4/16-medium)
- [-2, 1, Conv, [128, 1, 1]]
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P3
- [-1, 1, Bottleneck, [256, False]]
- [-1, 2, Bottleneck, [256, False]] # 27 (P3/8-small)
- [[27, 22, 15], 1, Detect, [nc]] # Detect(P3, P4, P5)

40
ultralytics/cfg/models/v3/yolov3-tiny.yaml Executable file
View File

@@ -0,0 +1,40 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLOv3-tiny object detection model with P4/16 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolov3
# Task docs: https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
depth_multiple: 1.0 # model depth multiple
width_multiple: 1.0 # layer channel multiple
# YOLOv3-tiny backbone
backbone:
# [from, number, module, args]
- [-1, 1, Conv, [16, 3, 1]] # 0
- [-1, 1, nn.MaxPool2d, [2, 2, 0]] # 1-P1/2
- [-1, 1, Conv, [32, 3, 1]]
- [-1, 1, nn.MaxPool2d, [2, 2, 0]] # 3-P2/4
- [-1, 1, Conv, [64, 3, 1]]
- [-1, 1, nn.MaxPool2d, [2, 2, 0]] # 5-P3/8
- [-1, 1, Conv, [128, 3, 1]]
- [-1, 1, nn.MaxPool2d, [2, 2, 0]] # 7-P4/16
- [-1, 1, Conv, [256, 3, 1]]
- [-1, 1, nn.MaxPool2d, [2, 2, 0]] # 9-P5/32
- [-1, 1, Conv, [512, 3, 1]]
- [-1, 1, nn.ZeroPad2d, [[0, 1, 0, 1]]] # 11
- [-1, 1, nn.MaxPool2d, [2, 1, 0]] # 12
# YOLOv3-tiny head
head:
- [-1, 1, Conv, [1024, 3, 1]]
- [-1, 1, Conv, [256, 1, 1]]
- [-1, 1, Conv, [512, 3, 1]] # 15 (P5/32-large)
- [-2, 1, Conv, [128, 1, 1]]
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 8], 1, Concat, [1]] # cat backbone P4
- [-1, 1, Conv, [256, 3, 1]] # 19 (P4/16-medium)
- [[19, 15], 1, Detect, [nc]] # Detect(P4, P5)

49
ultralytics/cfg/models/v3/yolov3.yaml Executable file
View File

@@ -0,0 +1,49 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLOv3 object detection model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolov3
# Task docs: https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
depth_multiple: 1.0 # model depth multiple
width_multiple: 1.0 # layer channel multiple
# darknet53 backbone
backbone:
# [from, number, module, args]
- [-1, 1, Conv, [32, 3, 1]] # 0
- [-1, 1, Conv, [64, 3, 2]] # 1-P1/2
- [-1, 1, Bottleneck, [64]]
- [-1, 1, Conv, [128, 3, 2]] # 3-P2/4
- [-1, 2, Bottleneck, [128]]
- [-1, 1, Conv, [256, 3, 2]] # 5-P3/8
- [-1, 8, Bottleneck, [256]]
- [-1, 1, Conv, [512, 3, 2]] # 7-P4/16
- [-1, 8, Bottleneck, [512]]
- [-1, 1, Conv, [1024, 3, 2]] # 9-P5/32
- [-1, 4, Bottleneck, [1024]] # 10
# YOLOv3 head
head:
- [-1, 1, Bottleneck, [1024, False]]
- [-1, 1, Conv, [512, 1, 1]]
- [-1, 1, Conv, [1024, 3, 1]]
- [-1, 1, Conv, [512, 1, 1]]
- [-1, 1, Conv, [1024, 3, 1]] # 15 (P5/32-large)
- [-2, 1, Conv, [256, 1, 1]]
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 8], 1, Concat, [1]] # cat backbone P4
- [-1, 1, Bottleneck, [512, False]]
- [-1, 1, Bottleneck, [512, False]]
- [-1, 1, Conv, [256, 1, 1]]
- [-1, 1, Conv, [512, 3, 1]] # 22 (P4/16-medium)
- [-2, 1, Conv, [128, 1, 1]]
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P3
- [-1, 1, Bottleneck, [256, False]]
- [-1, 2, Bottleneck, [256, False]] # 27 (P3/8-small)
- [[27, 22, 15], 1, Detect, [nc]] # Detect(P3, P4, P5)

62
ultralytics/cfg/models/v5/yolov5-p6.yaml Executable file
View File

@@ -0,0 +1,62 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLOv5 object detection model with P3/8 - P6/64 outputs
# Model docs: https://docs.ultralytics.com/models/yolov5
# Task docs: https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov5n-p6.yaml' will call yolov5-p6.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024]
s: [0.33, 0.50, 1024]
m: [0.67, 0.75, 1024]
l: [1.00, 1.00, 1024]
x: [1.33, 1.25, 1024]
# YOLOv5 v6.0 backbone
backbone:
# [from, number, module, args]
- [-1, 1, Conv, [64, 6, 2, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C3, [128]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C3, [256]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 9, C3, [512]]
- [-1, 1, Conv, [768, 3, 2]] # 7-P5/32
- [-1, 3, C3, [768]]
- [-1, 1, Conv, [1024, 3, 2]] # 9-P6/64
- [-1, 3, C3, [1024]]
- [-1, 1, SPPF, [1024, 5]] # 11
# YOLOv5 v6.0 head
head:
- [-1, 1, Conv, [768, 1, 1]]
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 8], 1, Concat, [1]] # cat backbone P5
- [-1, 3, C3, [768, False]] # 15
- [-1, 1, Conv, [512, 1, 1]]
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C3, [512, False]] # 19
- [-1, 1, Conv, [256, 1, 1]]
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C3, [256, False]] # 23 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 20], 1, Concat, [1]] # cat head P4
- [-1, 3, C3, [512, False]] # 26 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 16], 1, Concat, [1]] # cat head P5
- [-1, 3, C3, [768, False]] # 29 (P5/32-large)
- [-1, 1, Conv, [768, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P6
- [-1, 3, C3, [1024, False]] # 32 (P6/64-xlarge)
- [[23, 26, 29, 32], 1, Detect, [nc]] # Detect(P3, P4, P5, P6)

51
ultralytics/cfg/models/v5/yolov5.yaml Executable file
View File

@@ -0,0 +1,51 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLOv5 object detection model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolov5
# Task docs: https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov5n.yaml' will call yolov5.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024]
s: [0.33, 0.50, 1024]
m: [0.67, 0.75, 1024]
l: [1.00, 1.00, 1024]
x: [1.33, 1.25, 1024]
# YOLOv5 v6.0 backbone
backbone:
# [from, number, module, args]
- [-1, 1, Conv, [64, 6, 2, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C3, [128]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C3, [256]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 9, C3, [512]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C3, [1024]]
- [-1, 1, SPPF, [1024, 5]] # 9
# YOLOv5 v6.0 head
head:
- [-1, 1, Conv, [512, 1, 1]]
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C3, [512, False]] # 13
- [-1, 1, Conv, [256, 1, 1]]
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C3, [256, False]] # 17 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 14], 1, Concat, [1]] # cat head P4
- [-1, 3, C3, [512, False]] # 20 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 3, C3, [1024, False]] # 23 (P5/32-large)
- [[17, 20, 23], 1, Detect, [nc]] # Detect(P3, P4, P5)

56
ultralytics/cfg/models/v6/yolov6.yaml Executable file
View File

@@ -0,0 +1,56 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Meituan YOLOv6 object detection model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolov6
# Task docs: https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
activation: torch.nn.ReLU() # (optional) model default activation function
scales: # model compound scaling constants, i.e. 'model=yolov6n.yaml' will call yolov6.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024]
s: [0.33, 0.50, 1024]
m: [0.67, 0.75, 768]
l: [1.00, 1.00, 512]
x: [1.00, 1.25, 512]
# YOLOv6-3.0s backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 6, Conv, [128, 3, 1]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 12, Conv, [256, 3, 1]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 18, Conv, [512, 3, 1]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 6, Conv, [1024, 3, 1]]
- [-1, 1, SPPF, [1024, 5]] # 9
# YOLOv6-3.0s head
head:
- [-1, 1, Conv, [256, 1, 1]]
- [-1, 1, nn.ConvTranspose2d, [256, 2, 2, 0]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 1, Conv, [256, 3, 1]]
- [-1, 9, Conv, [256, 3, 1]] # 14
- [-1, 1, Conv, [128, 1, 1]]
- [-1, 1, nn.ConvTranspose2d, [128, 2, 2, 0]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 1, Conv, [128, 3, 1]]
- [-1, 9, Conv, [128, 3, 1]] # 19
- [-1, 1, Conv, [128, 3, 2]]
- [[-1, 15], 1, Concat, [1]] # cat head P4
- [-1, 1, Conv, [256, 3, 1]]
- [-1, 9, Conv, [256, 3, 1]] # 23
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 10], 1, Concat, [1]] # cat head P5
- [-1, 1, Conv, [512, 3, 1]]
- [-1, 9, Conv, [512, 3, 1]] # 27
- [[19, 23, 27], 1, Detect, [nc]] # Detect(P3, P4, P5)

48
ultralytics/cfg/models/v8/yoloe-v8-seg.yaml Executable file
View File

@@ -0,0 +1,48 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLOE-v8-seg instance segmentation model with P3/8 - P5/32 outputs
# Task docs: https://docs.ultralytics.com/tasks/segment
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yoloe-v8n-seg.yaml' will call yoloe-v8-seg.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024] # YOLOE-v8n-seg summary: 161 layers, 4204111 parameters, 4204095 gradients, 39.6 GFLOPs
s: [0.33, 0.50, 1024] # YOLOE-v8s-seg summary: 161 layers, 13383496 parameters, 13383480 gradients, 71.5 GFLOPs
m: [0.67, 0.75, 768] # YOLOE-v8m-seg summary: 201 layers, 29065310 parameters, 29065294 gradients, 131.4 GFLOPs
l: [1.00, 1.00, 512] # YOLOE-v8l-seg summary: 241 layers, 47553970 parameters, 47553954 gradients, 225.6 GFLOPs
x: [1.00, 1.25, 512] # YOLOE-v8x-seg summary: 241 layers, 73690217 parameters, 73690201 gradients, 330.8 GFLOPs
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 15 (P3/8-small)
- [15, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 18 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 21 (P5/32-large)
- [[15, 18, 21], 1, YOLOESegment, [nc, 32, 256, 512, True]] # YOLOESegment(P3, P4, P5)

48
ultralytics/cfg/models/v8/yoloe-v8.yaml Executable file
View File

@@ -0,0 +1,48 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLOE-v8 object detection model with P3/8 - P5/32 outputs
# Task docs: https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yoloe-v8n.yaml' will call yoloe-v8.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024] # YOLOE-v8n summary: 148 layers, 3695183 parameters, 3695167 gradients, 19.5 GFLOPs
s: [0.33, 0.50, 1024] # YOLOE-v8s summary: 148 layers, 12759880 parameters, 12759864 gradients, 51.0 GFLOPs
m: [0.67, 0.75, 768] # YOLOE-v8m summary: 188 layers, 28376158 parameters, 28376142 gradients, 110.5 GFLOPs
l: [1.00, 1.00, 512] # YOLOE-v8l summary: 228 layers, 46832050 parameters, 46832034 gradients, 204.5 GFLOPs
x: [1.00, 1.25, 512] # YOLOE-v8x summary: 228 layers, 72886377 parameters, 72886361 gradients, 309.3 GFLOPs
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 15 (P3/8-small)
- [15, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 18 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 21 (P5/32-large)
- [[15, 18, 21], 1, YOLOEDetect, [nc, 512, True]] # YOLOEDetect(P3, P4, P5)

28
ultralytics/cfg/models/v8/yolov8-cls-resnet101.yaml Executable file
View File

@@ -0,0 +1,28 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLOv8-cls image classification model with ResNet101 backbone
# Model docs: https://docs.ultralytics.com/models/yolov8
# Task docs: https://docs.ultralytics.com/tasks/classify
# Parameters
nc: 1000 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-cls-resnet101.yaml' will call yolov8-cls-resnet101.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024]
s: [0.33, 0.50, 1024]
m: [0.67, 0.75, 1024]
l: [1.00, 1.00, 1024]
x: [1.00, 1.25, 1024]
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, ResNetLayer, [3, 64, 1, True, 1]] # 0-P1/2
- [-1, 1, ResNetLayer, [64, 64, 1, False, 3]] # 1-P2/4
- [-1, 1, ResNetLayer, [256, 128, 2, False, 4]] # 2-P3/8
- [-1, 1, ResNetLayer, [512, 256, 2, False, 23]] # 3-P4/16
- [-1, 1, ResNetLayer, [1024, 512, 2, False, 3]] # 4-P5/32
# YOLOv8.0n head
head:
- [-1, 1, Classify, [nc]] # Classify

28
ultralytics/cfg/models/v8/yolov8-cls-resnet50.yaml Executable file
View File

@@ -0,0 +1,28 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLOv8-cls image classification model with ResNet50 backbone
# Model docs: https://docs.ultralytics.com/models/yolov8
# Task docs: https://docs.ultralytics.com/tasks/classify
# Parameters
nc: 1000 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-cls-resnet50.yaml' will call yolov8-cls-resnet50.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024]
s: [0.33, 0.50, 1024]
m: [0.67, 0.75, 1024]
l: [1.00, 1.00, 1024]
x: [1.00, 1.25, 1024]
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, ResNetLayer, [3, 64, 1, True, 1]] # 0-P1/2
- [-1, 1, ResNetLayer, [64, 64, 1, False, 3]] # 1-P2/4
- [-1, 1, ResNetLayer, [256, 128, 2, False, 4]] # 2-P3/8
- [-1, 1, ResNetLayer, [512, 256, 2, False, 6]] # 3-P4/16
- [-1, 1, ResNetLayer, [1024, 512, 2, False, 3]] # 4-P5/32
# YOLOv8.0n head
head:
- [-1, 1, Classify, [nc]] # Classify

32
ultralytics/cfg/models/v8/yolov8-cls.yaml Executable file
View File

@@ -0,0 +1,32 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLOv8-cls image classification model with YOLO backbone
# Model docs: https://docs.ultralytics.com/models/yolov8
# Task docs: https://docs.ultralytics.com/tasks/classify
# Parameters
nc: 1000 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024]
s: [0.33, 0.50, 1024]
m: [0.67, 0.75, 1024]
l: [1.00, 1.00, 1024]
x: [1.00, 1.25, 1024]
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [1024, True]]
# YOLOv8.0n head
head:
- [-1, 1, Classify, [nc]] # Classify

58
ultralytics/cfg/models/v8/yolov8-ghost-p2.yaml Executable file
View File

@@ -0,0 +1,58 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLOv8-ghost object detection model with P2/4 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolov8
# Task docs: https://docs.ultralytics.com/tasks/detect
# Employs Ghost convolutions and modules proposed in Huawei's GhostNet in https://arxiv.org/abs/1911.11907v2
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-ghost-p2.yaml' will call yolov8-ghost-p2.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024] # YOLOv8n-ghost-p2 summary: 290 layers, 2033944 parameters, 2033928 gradients, 13.8 GFLOPs
s: [0.33, 0.50, 1024] # YOLOv8s-ghost-p2 summary: 290 layers, 5562080 parameters, 5562064 gradients, 25.1 GFLOPs
m: [0.67, 0.75, 768] # YOLOv8m-ghost-p2 summary: 434 layers, 9031728 parameters, 9031712 gradients, 42.8 GFLOPs
l: [1.00, 1.00, 512] # YOLOv8l-ghost-p2 summary: 578 layers, 12214448 parameters, 12214432 gradients, 69.1 GFLOPs
x: [1.00, 1.25, 512] # YOLOv8x-ghost-p2 summary: 578 layers, 18664776 parameters, 18664760 gradients, 103.3 GFLOPs
# YOLOv8.0-ghost backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, GhostConv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C3Ghost, [128, True]]
- [-1, 1, GhostConv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C3Ghost, [256, True]]
- [-1, 1, GhostConv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C3Ghost, [512, True]]
- [-1, 1, GhostConv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C3Ghost, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
# YOLOv8.0-ghost-p2 head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C3Ghost, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C3Ghost, [256]] # 15 (P3/8-small)
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 2], 1, Concat, [1]] # cat backbone P2
- [-1, 3, C3Ghost, [128]] # 18 (P2/4-xsmall)
- [-1, 1, GhostConv, [128, 3, 2]]
- [[-1, 15], 1, Concat, [1]] # cat head P3
- [-1, 3, C3Ghost, [256]] # 21 (P3/8-small)
- [-1, 1, GhostConv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C3Ghost, [512]] # 24 (P4/16-medium)
- [-1, 1, GhostConv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C3Ghost, [1024]] # 27 (P5/32-large)
- [[18, 21, 24, 27], 1, Detect, [nc]] # Detect(P2, P3, P4, P5)

60
ultralytics/cfg/models/v8/yolov8-ghost-p6.yaml Executable file
View File

@@ -0,0 +1,60 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLOv8-ghost object detection model with P3/8 - P6/64 outputs
# Model docs: https://docs.ultralytics.com/models/yolov8
# Task docs: https://docs.ultralytics.com/tasks/detect
# Employs Ghost convolutions and modules proposed in Huawei's GhostNet in https://arxiv.org/abs/1911.11907v2
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-ghost-p6.yaml' will call yolov8-ghost-p6.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024] # YOLOv8n-ghost-p6 summary: 312 layers, 2901100 parameters, 2901084 gradients, 5.8 GFLOPs
s: [0.33, 0.50, 1024] # YOLOv8s-ghost-p6 summary: 312 layers, 9520008 parameters, 9519992 gradients, 16.4 GFLOPs
m: [0.67, 0.75, 768] # YOLOv8m-ghost-p6 summary: 468 layers, 18002904 parameters, 18002888 gradients, 34.4 GFLOPs
l: [1.00, 1.00, 512] # YOLOv8l-ghost-p6 summary: 624 layers, 21227584 parameters, 21227568 gradients, 55.3 GFLOPs
x: [1.00, 1.25, 512] # YOLOv8x-ghost-p6 summary: 624 layers, 33057852 parameters, 33057836 gradients, 85.7 GFLOPs
# YOLOv8.0-ghost backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, GhostConv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C3Ghost, [128, True]]
- [-1, 1, GhostConv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C3Ghost, [256, True]]
- [-1, 1, GhostConv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C3Ghost, [512, True]]
- [-1, 1, GhostConv, [768, 3, 2]] # 7-P5/32
- [-1, 3, C3Ghost, [768, True]]
- [-1, 1, GhostConv, [1024, 3, 2]] # 9-P6/64
- [-1, 3, C3Ghost, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 11
# YOLOv8.0-ghost-p6 head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 8], 1, Concat, [1]] # cat backbone P5
- [-1, 3, C3Ghost, [768]] # 14
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C3Ghost, [512]] # 17
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C3Ghost, [256]] # 20 (P3/8-small)
- [-1, 1, GhostConv, [256, 3, 2]]
- [[-1, 17], 1, Concat, [1]] # cat head P4
- [-1, 3, C3Ghost, [512]] # 23 (P4/16-medium)
- [-1, 1, GhostConv, [512, 3, 2]]
- [[-1, 14], 1, Concat, [1]] # cat head P5
- [-1, 3, C3Ghost, [768]] # 26 (P5/32-large)
- [-1, 1, GhostConv, [768, 3, 2]]
- [[-1, 11], 1, Concat, [1]] # cat head P6
- [-1, 3, C3Ghost, [1024]] # 29 (P6/64-xlarge)
- [[20, 23, 26, 29], 1, Detect, [nc]] # Detect(P3, P4, P5, P6)

50
ultralytics/cfg/models/v8/yolov8-ghost.yaml Executable file
View File

@@ -0,0 +1,50 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLOv8-ghost object detection model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolov8
# Task docs: https://docs.ultralytics.com/tasks/detect
# Employs Ghost convolutions and modules proposed in Huawei's GhostNet in https://arxiv.org/abs/1911.11907v2
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-ghost.yaml' will call yolov8-ghost.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024] # YOLOv8n-ghost summary: 237 layers, 1865316 parameters, 1865300 gradients, 5.8 GFLOPs
s: [0.33, 0.50, 1024] # YOLOv8s-ghost summary: 237 layers, 5960072 parameters, 5960056 gradients, 16.4 GFLOPs
m: [0.67, 0.75, 768] # YOLOv8m-ghost summary: 357 layers, 10336312 parameters, 10336296 gradients, 32.7 GFLOPs
l: [1.00, 1.00, 512] # YOLOv8l-ghost summary: 477 layers, 14277872 parameters, 14277856 gradients, 53.7 GFLOPs
x: [1.00, 1.25, 512] # YOLOv8x-ghost summary: 477 layers, 22229308 parameters, 22229292 gradients, 83.3 GFLOPs
# YOLOv8.0n-ghost backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, GhostConv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C3Ghost, [128, True]]
- [-1, 1, GhostConv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C3Ghost, [256, True]]
- [-1, 1, GhostConv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C3Ghost, [512, True]]
- [-1, 1, GhostConv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C3Ghost, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C3Ghost, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C3Ghost, [256]] # 15 (P3/8-small)
- [-1, 1, GhostConv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C3Ghost, [512]] # 18 (P4/16-medium)
- [-1, 1, GhostConv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C3Ghost, [1024]] # 21 (P5/32-large)
- [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5)

49
ultralytics/cfg/models/v8/yolov8-obb.yaml Executable file
View File

@@ -0,0 +1,49 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLOv8-obb Oriented Bounding Boxes (OBB) model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolov8
# Task docs: https://docs.ultralytics.com/tasks/obb
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-obb.yaml' will call yolov8-obb.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024] # YOLOv8n-obb summary: 144 layers, 3228867 parameters, 3228851 gradients, 9.1 GFLOPs
s: [0.33, 0.50, 1024] # YOLOv8s-obb summary: 144 layers, 11452739 parameters, 11452723 gradients, 29.8 GFLOPs
m: [0.67, 0.75, 768] # YOLOv8m-obb summary: 184 layers, 26463235 parameters, 26463219 gradients, 81.5 GFLOPs
l: [1.00, 1.00, 512] # YOLOv8l-obb summary: 224 layers, 44540355 parameters, 44540339 gradients, 169.4 GFLOPs
x: [1.00, 1.25, 512] # YOLOv8x-obb summary: 224 layers, 69555651 parameters, 69555635 gradients, 264.3 GFLOPs
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 15 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 18 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 21 (P5/32-large)
- [[15, 18, 21], 1, OBB, [nc, 1]] # OBB(P3, P4, P5)

57
ultralytics/cfg/models/v8/yolov8-p2.yaml Executable file
View File

@@ -0,0 +1,57 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLOv8 object detection model with P2/4 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolov8
# Task docs: https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-p2.yaml' will call yolov8-p2.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024]
s: [0.33, 0.50, 1024]
m: [0.67, 0.75, 768]
l: [1.00, 1.00, 512]
x: [1.00, 1.25, 512]
# YOLOv8.0 backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
# YOLOv8.0-p2 head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 15 (P3/8-small)
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 2], 1, Concat, [1]] # cat backbone P2
- [-1, 3, C2f, [128]] # 18 (P2/4-xsmall)
- [-1, 1, Conv, [128, 3, 2]]
- [[-1, 15], 1, Concat, [1]] # cat head P3
- [-1, 3, C2f, [256]] # 21 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 24 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 27 (P5/32-large)
- [[18, 21, 24, 27], 1, Detect, [nc]] # Detect(P2, P3, P4, P5)

59
ultralytics/cfg/models/v8/yolov8-p6.yaml Executable file
View File

@@ -0,0 +1,59 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLOv8 object detection model with P3/8 - P6/64 outputs
# Model docs: https://docs.ultralytics.com/models/yolov8
# Task docs: https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-p6.yaml' will call yolov8-p6.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024] # YOLOv8n-p6 summary: 170 layers, 4984352 parameters, 4984336 gradients, 8.8 GFLOPs
s: [0.33, 0.50, 1024] # YOLOv8s-p6 summary: 170 layers, 17911792 parameters, 17911776 gradients, 28.7 GFLOPs
m: [0.67, 0.75, 768] # YOLOv8m-p6 summary: 222 layers, 44887488 parameters, 44887472 gradients, 83.5 GFLOPs
l: [1.00, 1.00, 512] # YOLOv8l-p6 summary: 274 layers, 62384016 parameters, 62384000 gradients, 167.9 GFLOPs
x: [1.00, 1.25, 512] # YOLOv8x-p6 summary: 274 layers, 97423072 parameters, 97423056 gradients, 261.8 GFLOPs
# YOLOv8.0x6 backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, Conv, [768, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [768, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 9-P6/64
- [-1, 3, C2f, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 11
# YOLOv8.0x6 head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 8], 1, Concat, [1]] # cat backbone P5
- [-1, 3, C2, [768, False]] # 14
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2, [512, False]] # 17
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2, [256, False]] # 20 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 17], 1, Concat, [1]] # cat head P4
- [-1, 3, C2, [512, False]] # 23 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 14], 1, Concat, [1]] # cat head P5
- [-1, 3, C2, [768, False]] # 26 (P5/32-large)
- [-1, 1, Conv, [768, 3, 2]]
- [[-1, 11], 1, Concat, [1]] # cat head P6
- [-1, 3, C2, [1024, False]] # 29 (P6/64-xlarge)
- [[20, 23, 26, 29], 1, Detect, [nc]] # Detect(P3, P4, P5, P6)

60
ultralytics/cfg/models/v8/yolov8-pose-p6.yaml Executable file
View File

@@ -0,0 +1,60 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLOv8-pose keypoints/pose estimation model with P3/8 - P6/64 outputs
# Model docs: https://docs.ultralytics.com/models/yolov8
# Task docs: https://docs.ultralytics.com/tasks/pose
# Parameters
nc: 1 # number of classes
kpt_shape: [17, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
scales: # model compound scaling constants, i.e. 'model=yolov8n-pose-p6.yaml' will call yolov8-pose-p6.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024]
s: [0.33, 0.50, 1024]
m: [0.67, 0.75, 768]
l: [1.00, 1.00, 512]
x: [1.00, 1.25, 512]
# YOLOv8.0x6 backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, Conv, [768, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [768, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 9-P6/64
- [-1, 3, C2f, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 11
# YOLOv8.0x6 head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 8], 1, Concat, [1]] # cat backbone P5
- [-1, 3, C2, [768, False]] # 14
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2, [512, False]] # 17
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2, [256, False]] # 20 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 17], 1, Concat, [1]] # cat head P4
- [-1, 3, C2, [512, False]] # 23 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 14], 1, Concat, [1]] # cat head P5
- [-1, 3, C2, [768, False]] # 26 (P5/32-large)
- [-1, 1, Conv, [768, 3, 2]]
- [[-1, 11], 1, Concat, [1]] # cat head P6
- [-1, 3, C2, [1024, False]] # 29 (P6/64-xlarge)
- [[20, 23, 26, 29], 1, Pose, [nc, kpt_shape]] # Pose(P3, P4, P5, P6)

50
ultralytics/cfg/models/v8/yolov8-pose.yaml Executable file
View File

@@ -0,0 +1,50 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLOv8-pose keypoints/pose estimation model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolov8
# Task docs: https://docs.ultralytics.com/tasks/pose
# Parameters
nc: 1 # number of classes
kpt_shape: [17, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
scales: # model compound scaling constants, i.e. 'model=yolov8n-pose.yaml' will call yolov8-pose.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024]
s: [0.33, 0.50, 1024]
m: [0.67, 0.75, 768]
l: [1.00, 1.00, 512]
x: [1.00, 1.25, 512]
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 15 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 18 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 21 (P5/32-large)
- [[15, 18, 21], 1, Pose, [nc, kpt_shape]] # Pose(P3, P4, P5)

49
ultralytics/cfg/models/v8/yolov8-rtdetr.yaml Executable file
View File

@@ -0,0 +1,49 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLOv8-RTDETR hybrid object detection model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/rtdetr
# Task docs: https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-rtdetr.yaml' will call yolov8-rtdetr.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024] # YOLOv8n-rtdetr summary: 235 layers, 9643868 parameters, 9643868 gradients, 17.1 GFLOPs
s: [0.33, 0.50, 1024] # YOLOv8s-rtdetr summary: 235 layers, 16518572 parameters, 16518572 gradients, 32.8 GFLOPs
m: [0.67, 0.75, 768] # YOLOv8m-rtdetr summary: 275 layers, 29645180 parameters, 29645180 gradients, 75.8 GFLOPs
l: [1.00, 1.00, 512] # YOLOv8l-rtdetr summary: 315 layers, 45644364 parameters, 45644364 gradients, 152.3 GFLOPs
x: [1.00, 1.25, 512] # YOLOv8x-rtdetr summary: 315 layers, 67113884 parameters, 67113884 gradients, 230.8 GFLOPs
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 15 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 18 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 21 (P5/32-large)
- [[15, 18, 21], 1, RTDETRDecoder, [nc]] # RTDETRDecoder(P3, P4, P5)

59
ultralytics/cfg/models/v8/yolov8-seg-p6.yaml Executable file
View File

@@ -0,0 +1,59 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLOv8-seg instance segmentation model with P3/8 - P6/64 outputs
# Model docs: https://docs.ultralytics.com/models/yolov8
# Task docs: https://docs.ultralytics.com/tasks/segment
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-seg-p6.yaml' will call yolov8-seg-p6.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024]
s: [0.33, 0.50, 1024]
m: [0.67, 0.75, 768]
l: [1.00, 1.00, 512]
x: [1.00, 1.25, 512]
# YOLOv8.0x6 backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, Conv, [768, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [768, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 9-P6/64
- [-1, 3, C2f, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 11
# YOLOv8.0x6 head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 8], 1, Concat, [1]] # cat backbone P5
- [-1, 3, C2, [768, False]] # 14
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2, [512, False]] # 17
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2, [256, False]] # 20 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 17], 1, Concat, [1]] # cat head P4
- [-1, 3, C2, [512, False]] # 23 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 14], 1, Concat, [1]] # cat head P5
- [-1, 3, C2, [768, False]] # 26 (P5/32-large)
- [-1, 1, Conv, [768, 3, 2]]
- [[-1, 11], 1, Concat, [1]] # cat head P6
- [-1, 3, C2, [1024, False]] # 29 (P6/64-xlarge)
- [[20, 23, 26, 29], 1, Segment, [nc, 32, 256]] # Segment(P3, P4, P5, P6)

49
ultralytics/cfg/models/v8/yolov8-seg.yaml Executable file
View File

@@ -0,0 +1,49 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLOv8-seg instance segmentation model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolov8
# Task docs: https://docs.ultralytics.com/tasks/segment
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-seg.yaml' will call yolov8-seg.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024]
s: [0.33, 0.50, 1024]
m: [0.67, 0.75, 768]
l: [1.00, 1.00, 512]
x: [1.00, 1.25, 512]
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2f, [512]] # 12
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2f, [256]] # 15 (P3/8-small)
- [-1, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2f, [512]] # 18 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2f, [1024]] # 21 (P5/32-large)
- [[15, 18, 21], 1, Segment, [nc, 32, 256]] # Segment(P3, P4, P5)

51
ultralytics/cfg/models/v8/yolov8-world.yaml Executable file
View File

@@ -0,0 +1,51 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLOv8-World hybrid object detection model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolo-world
# Task docs: https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-world.yaml' will call yolov8-world.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024] # YOLOv8n-world summary: 161 layers, 4204111 parameters, 4204095 gradients, 39.6 GFLOPs
s: [0.33, 0.50, 1024] # YOLOv8s-world summary: 161 layers, 13383496 parameters, 13383480 gradients, 71.5 GFLOPs
m: [0.67, 0.75, 768] # YOLOv8m-world summary: 201 layers, 29065310 parameters, 29065294 gradients, 131.4 GFLOPs
l: [1.00, 1.00, 512] # YOLOv8l-world summary: 241 layers, 47553970 parameters, 47553954 gradients, 225.6 GFLOPs
x: [1.00, 1.25, 512] # YOLOv8x-world summary: 241 layers, 73690217 parameters, 73690201 gradients, 330.8 GFLOPs
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2fAttn, [512, 256, 8]] # 12
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2fAttn, [256, 128, 4]] # 15 (P3/8-small)
- [[15, 12, 9], 1, ImagePoolingAttn, [256]] # 16 (P3/8-small)
- [15, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2fAttn, [512, 256, 8]] # 19 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2fAttn, [1024, 512, 16]] # 22 (P5/32-large)
- [[15, 19, 22], 1, WorldDetect, [nc, 512, False]] # WorldDetect(P3, P4, P5)

49
ultralytics/cfg/models/v8/yolov8-worldv2.yaml Executable file
View File

@@ -0,0 +1,49 @@
# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
# Ultralytics YOLOv8-Worldv2 hybrid object detection model with P3/8 - P5/32 outputs
# Model docs: https://docs.ultralytics.com/models/yolo-world
# Task docs: https://docs.ultralytics.com/tasks/detect
# Parameters
nc: 80 # number of classes
scales: # model compound scaling constants, i.e. 'model=yolov8n-worldv2.yaml' will call yolov8-worldv2.yaml with scale 'n'
# [depth, width, max_channels]
n: [0.33, 0.25, 1024] # YOLOv8n-worldv2 summary: 148 layers, 3695183 parameters, 3695167 gradients, 19.5 GFLOPs
s: [0.33, 0.50, 1024] # YOLOv8s-worldv2 summary: 148 layers, 12759880 parameters, 12759864 gradients, 51.0 GFLOPs
m: [0.67, 0.75, 768] # YOLOv8m-worldv2 summary: 188 layers, 28376158 parameters, 28376142 gradients, 110.5 GFLOPs
l: [1.00, 1.00, 512] # YOLOv8l-worldv2 summary: 228 layers, 46832050 parameters, 46832034 gradients, 204.5 GFLOPs
x: [1.00, 1.25, 512] # YOLOv8x-worldv2 summary: 228 layers, 72886377 parameters, 72886361 gradients, 309.3 GFLOPs
# YOLOv8.0n backbone
backbone:
# [from, repeats, module, args]
- [-1, 1, Conv, [64, 3, 2]] # 0-P1/2
- [-1, 1, Conv, [128, 3, 2]] # 1-P2/4
- [-1, 3, C2f, [128, True]]
- [-1, 1, Conv, [256, 3, 2]] # 3-P3/8
- [-1, 6, C2f, [256, True]]
- [-1, 1, Conv, [512, 3, 2]] # 5-P4/16
- [-1, 6, C2f, [512, True]]
- [-1, 1, Conv, [1024, 3, 2]] # 7-P5/32
- [-1, 3, C2f, [1024, True]]
- [-1, 1, SPPF, [1024, 5]] # 9
# YOLOv8.0n head
head:
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 6], 1, Concat, [1]] # cat backbone P4
- [-1, 3, C2fAttn, [512, 256, 8]] # 12
- [-1, 1, nn.Upsample, [None, 2, "nearest"]]
- [[-1, 4], 1, Concat, [1]] # cat backbone P3
- [-1, 3, C2fAttn, [256, 128, 4]] # 15 (P3/8-small)
- [15, 1, Conv, [256, 3, 2]]
- [[-1, 12], 1, Concat, [1]] # cat head P4
- [-1, 3, C2fAttn, [512, 256, 8]] # 18 (P4/16-medium)
- [-1, 1, Conv, [512, 3, 2]]
- [[-1, 9], 1, Concat, [1]] # cat head P5
- [-1, 3, C2fAttn, [1024, 512, 16]] # 21 (P5/32-large)
- [[15, 18, 21], 1, WorldDetect, [nc, 512, True]] # WorldDetect(P3, P4, P5)

Some files were not shown because too many files have changed in this diff Show More