Merge 84128a569e3d21b132163ed8ff713262680a0441 into 453c6e38a51e9d1d5a2aa5fb7f1014a711913397

ultralytics/__init__.py

@@ -3,7 +3,7 @@
 __version__ = "8.1.34"
 
 from ultralytics.data.explorer.explorer import Explorer
-from ultralytics.models import RTDETR, SAM, YOLO, YOLOWorld, YOLOv10
+from ultralytics.models import RTDETR, SAM, YOLO, YOLOWorld, YOLOv10,YOLOv10Seg
 from ultralytics.models.fastsam import FastSAM
 from ultralytics.models.nas import NAS
 from ultralytics.utils import ASSETS, SETTINGS as settings

ultralytics/cfg/datasets/Argoverse.yaml

@@ -1,74 +0,0 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
-# Argoverse-HD dataset (ring-front-center camera) https://www.cs.cmu.edu/~mengtial/proj/streaming/ by Argo AI
-# 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: ../datasets/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 tqdm import tqdm
-  from ultralytics.utils.downloads import download
-  from pathlib import Path
-
-  def argoverse2yolo(set):
-      labels = {}
-      a = json.load(open(set, "rb"))
-      for annot in tqdm(a['annotations'], desc=f"Converting {set} to YOLOv5 format..."):
-          img_id = annot['image_id']
-          img_name = a['images'][img_id]['name']
-          img_label_name = f'{img_name[:-3]}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 = set.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") 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

ultralytics/cfg/datasets/DOTAv1.5.yaml

@@ -1,36 +0,0 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 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 (2GB)
-
-# 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: ../datasets/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/yolov5/releases/download/v1.0/DOTAv1.5.zip

ultralytics/cfg/datasets/DOTAv1.yaml

@@ -1,35 +0,0 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 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 (2GB)
-
-# 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: ../datasets/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/yolov5/releases/download/v1.0/DOTAv1.zip

ultralytics/cfg/datasets/GlobalWheat2020.yaml

@@ -1,53 +0,0 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 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: ../datasets/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 ultralytics.utils.downloads import download
-  from pathlib import Path
-
-  # Download
-  dir = Path(yaml['path'])  # dataset root dir
-  urls = ['https://zenodo.org/record/4298502/files/global-wheat-codalab-official.zip',
-          'https://github.com/ultralytics/yolov5/releases/download/v1.0/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

ultralytics/cfg/datasets/Objects365.yaml

@@ -1,442 +0,0 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 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: ../datasets/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: Dinning 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: Hamimelon
-  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: Meat ball
-  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 tqdm import tqdm
-
-  from ultralytics.utils.checks import check_requirements
-  from ultralytics.utils.downloads import download
-  from ultralytics.utils.ops import xyxy2xywhn
-
-  import numpy as np
-  from pathlib import Path
-
-  check_requirements(('pycocotools>=2.0',))
-  from pycocotools.coco import COCO
-
-  # Make Directories
-  dir = Path(yaml['path'])  # dataset root dir
-  for p in 'images', 'labels':
-      (dir / p).mkdir(parents=True, exist_ok=True)
-      for q in 'train', 'val':
-          (dir / p / q).mkdir(parents=True, exist_ok=True)
-
-  # Train, Val Splits
-  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
-
-      # 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, curl=True, threads=8)
-      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, curl=True, threads=8)
-          download([f'{url}images/v2/patch{i}.tar.gz' for i in range(16, patches)], dir=images, curl=True, threads=8)
-
-      # Move
-      for f in tqdm(images.rglob('*.jpg'), desc=f'Moving {split} images'):
-          f.rename(images / f.name)  # move to /images/{split}
-
-      # 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)
-          for im in tqdm(coco.loadImgs(imgIds), desc=f'Class {cid + 1}/{len(names)} {cat}'):
-              width, height = im["width"], im["height"]
-              path = Path(im["file_name"])  # image filename
-              try:
-                  with open(labels / path.with_suffix('.txt').name, 'a') 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)

ultralytics/cfg/datasets/SKU-110K.yaml

@@ -1,57 +0,0 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 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: ../datasets/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 pandas as pd
-  from tqdm 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 = pd.read_csv(dir / 'annotations' / d, names=names).values  # annotations
-      images, unique_images = x[:, 0], np.unique(x[:, 0])
-      with open((dir / d).with_suffix('.txt').__str__().replace('annotations_', ''), 'w') 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') 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

ultralytics/cfg/datasets/VOC.yaml

@@ -1,99 +0,0 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
-# PASCAL VOC dataset http://host.robots.ox.ac.uk/pascal/VOC by University of Oxford
-# Documentation: # 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: ../datasets/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 tqdm import tqdm
-  from ultralytics.utils.downloads import download
-  from pathlib import Path
-
-  def convert_label(path, lb_path, year, image_id):
-      def convert_box(size, box):
-          dw, dh = 1. / size[0], 1. / 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
-
-      in_file = open(path / f'VOC{year}/Annotations/{image_id}.xml')
-      out_file = open(lb_path, 'w')
-      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
-  url = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/'
-  urls = [f'{url}VOCtrainval_06-Nov-2007.zip',  # 446MB, 5012 images
-          f'{url}VOCtest_06-Nov-2007.zip',  # 438MB, 4953 images
-          f'{url}VOCtrainval_11-May-2012.zip']  # 1.95GB, 17126 images
-  download(urls, dir=dir / 'images', curl=True, threads=3, exist_ok=True)  # download and unzip over existing paths (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

ultralytics/cfg/datasets/VisDrone.yaml

@@ -1,72 +0,0 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 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: ../datasets/VisDrone # dataset root dir
-train: VisDrone2019-DET-train/images # train images (relative to 'path')  6471 images
-val: VisDrone2019-DET-val/images # val images (relative to 'path')  548 images
-test: VisDrone2019-DET-test-dev/images # test 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
-
-  from ultralytics.utils.downloads import download
-
-  def visdrone2yolo(dir):
-      from PIL import Image
-      from tqdm import tqdm
-
-      def convert_box(size, box):
-          # Convert VisDrone box to YOLO xywh box
-          dw = 1. / size[0]
-          dh = 1. / size[1]
-          return (box[0] + box[2] / 2) * dw, (box[1] + box[3] / 2) * dh, box[2] * dw, box[3] * dh
-
-      (dir / 'labels').mkdir(parents=True, exist_ok=True)  # make labels directory
-      pbar = tqdm((dir / 'annotations').glob('*.txt'), desc=f'Converting {dir}')
-      for f in pbar:
-          img_size = Image.open((dir / 'images' / f.name).with_suffix('.jpg')).size
-          lines = []
-          with open(f, 'r') as file:  # read annotation.txt
-              for row in [x.split(',') for x in file.read().strip().splitlines()]:
-                  if row[4] == '0':  # VisDrone 'ignored regions' class 0
-                      continue
-                  cls = int(row[5]) - 1
-                  box = convert_box(img_size, tuple(map(int, row[:4])))
-                  lines.append(f"{cls} {' '.join(f'{x:.6f}' for x in box)}\n")
-                  with open(str(f).replace(f'{os.sep}annotations{os.sep}', f'{os.sep}labels{os.sep}'), 'w') as fl:
-                      fl.writelines(lines)  # write label.txt
-
-
-  # Download
-  dir = Path(yaml['path'])  # dataset root dir
-  urls = ['https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-train.zip',
-          'https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-val.zip',
-          'https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-test-dev.zip',
-          'https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-test-challenge.zip']
-  download(urls, dir=dir, curl=True, threads=4)
-
-  # Convert
-  for d in 'VisDrone2019-DET-train', 'VisDrone2019-DET-val', 'VisDrone2019-DET-test-dev':
-      visdrone2yolo(dir / d)  # convert VisDrone annotations to YOLO labels

ultralytics/cfg/datasets/african-wildlife.yaml

@@ -1,24 +0,0 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 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: ../datasets/african-wildlife # dataset root dir
-train: train/images # train images (relative to 'path') 1052 images
-val: valid/images # val images (relative to 'path') 225 images
-test: test/images # test images (relative to 'path') 227 images
-
-# Classes
-names:
-  0: buffalo
-  1: elephant
-  2: rhino
-  3: zebra
-
-# Download script/URL (optional)
-download: https://ultralytics.com/assets/african-wildlife.zip

ultralytics/cfg/datasets/brain-tumor.yaml

@@ -1,22 +0,0 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 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 (4.05 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: ../datasets/brain-tumor # dataset root dir
-train: train/images # train images (relative to 'path') 893 images
-val: valid/images # val images (relative to 'path') 223 images
-test: # test images (relative to 'path')
-
-# Classes
-names:
-  0: negative
-  1: positive
-
-# Download script/URL (optional)
-download: https://ultralytics.com/assets/brain-tumor.zip

ultralytics/cfg/datasets/carparts-seg.yaml

@@ -1,43 +0,0 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 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 (132 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: ../datasets/carparts-seg # dataset root dir
-train: train/images # train images (relative to 'path') 3516 images
-val: valid/images # val images (relative to 'path') 276 images
-test: test/images # 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://ultralytics.com/assets/carparts-seg.zip

ultralytics/cfg/datasets/coco-pose.yaml

@@ -1,38 +0,0 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
-# COCO 2017 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: ../datasets/coco-pose # 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
-
-# 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
-
-# Download script/URL (optional)
-download: |
-  from ultralytics.utils.downloads import download
-  from pathlib import Path
-
-  # Download labels
-  dir = Path(yaml['path'])  # dataset root dir
-  url = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/'
-  urls = [url + 'coco2017labels-pose.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)

ultralytics/cfg/datasets/coco.yaml

@@ -1,114 +0,0 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 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: ../datasets/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 ultralytics.utils.downloads import download
-  from pathlib import Path
-
-  # Download labels
-  segments = True  # segment or box labels
-  dir = Path(yaml['path'])  # dataset root dir
-  url = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/'
-  urls = [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)

ultralytics/cfg/datasets/coco128-seg.yaml

@@ -1,100 +0,0 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
-# COCO128-seg dataset https://www.kaggle.com/ultralytics/coco128 (first 128 images from COCO train2017) by Ultralytics
-# Documentation: https://docs.ultralytics.com/datasets/segment/coco/
-# Example usage: yolo train data=coco128.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: ../datasets/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://ultralytics.com/assets/coco128-seg.zip

ultralytics/cfg/datasets/coco128.yaml

@@ -1,100 +0,0 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
-# COCO128 dataset https://www.kaggle.com/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: ../datasets/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://ultralytics.com/assets/coco128.zip

ultralytics/cfg/datasets/coco8-pose.yaml

@@ -1,25 +0,0 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 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: ../datasets/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
-
-# Download script/URL (optional)
-download: https://ultralytics.com/assets/coco8-pose.zip

ultralytics/cfg/datasets/coco8-seg.yaml

@@ -1,100 +0,0 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 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: ../datasets/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://ultralytics.com/assets/coco8-seg.zip

ultralytics/cfg/datasets/coco8.yaml

@@ -1,100 +0,0 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 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: ../datasets/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://ultralytics.com/assets/coco8.zip

ultralytics/cfg/datasets/crack-seg.yaml

@@ -1,21 +0,0 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 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 (91.2 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: ../datasets/crack-seg # dataset root dir
-train: train/images # train images (relative to 'path') 3717 images
-val: valid/images # val images (relative to 'path') 112 images
-test: test/images # test images (relative to 'path') 200 images
-
-# Classes
-names:
-  0: crack
-
-# Download script/URL (optional)
-download: https://ultralytics.com/assets/crack-seg.zip

ultralytics/cfg/datasets/dota8.yaml

@@ -1,34 +0,0 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
-# DOTA8 dataset 8 images from split DOTAv1 dataset 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 (1MB)
-
-# 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: ../datasets/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/yolov5/releases/download/v1.0/dota8.zip

ultralytics/cfg/datasets/open-images-v7.yaml

@@ -1,660 +0,0 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 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: ../datasets/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: Doughnut
-  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: |
-  from ultralytics.utils import LOGGER, SETTINGS, Path, is_ubuntu, get_ubuntu_version
-  from ultralytics.utils.checks import check_requirements, check_version
-
-  check_requirements('fiftyone')
-  if is_ubuntu() and check_version(get_ubuntu_version(), '>=22.04'):
-      # Ubuntu>=22.04 patch https://github.com/voxel51/fiftyone/issues/2961#issuecomment-1666519347
-      check_requirements('fiftyone-db-ubuntu2204')
-
-  import fiftyone as fo
-  import fiftyone.zoo as foz
-  import warnings
-
-  name = 'open-images-v7'
-  fraction = 1.0  # fraction of full dataset to use
-  LOGGER.warning('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'],
-                                     dataset_dir=Path(SETTINGS['datasets_dir']) / 'fiftyone' / name,
-                                     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)

ultralytics/cfg/datasets/package-seg.yaml

@@ -1,21 +0,0 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 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 (102 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: ../datasets/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: test/images # test images (relative to 'path') 188 images
-
-# Classes
-names:
-  0: package
-
-# Download script/URL (optional)
-download: https://ultralytics.com/assets/package-seg.zip

ultralytics/cfg/datasets/tiger-pose.yaml

@@ -1,24 +0,0 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 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 (75.3 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: ../datasets/tiger-pose # dataset root dir
-train: train # train images (relative to 'path') 210 images
-val: 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
-
-# Download script/URL (optional)
-download: https://ultralytics.com/assets/tiger-pose.zip

ultralytics/cfg/datasets/xView.yaml

@@ -1,152 +0,0 @@
-# Ultralytics YOLO 🚀, AGPL-3.0 license
-# DIUx xView 2018 Challenge https://challenge.xviewdataset.org by U.S. National Geospatial-Intelligence Agency (NGA)
-# --------  DOWNLOAD DATA MANUALLY and jar xf val_images.zip to 'datasets/xView' before running 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: ../datasets/xView # dataset root dir
-train: images/autosplit_train.txt # train images (relative to 'path') 90% of 847 train images
-val: images/autosplit_val.txt # train 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
-  import os
-  from pathlib import Path
-
-  import numpy as np
-  from PIL import Image
-  from tqdm import tqdm
-
-  from ultralytics.data.utils import autosplit
-  from ultralytics.utils.ops import xyxy2xywhn
-
-
-  def convert_labels(fname=Path('xView/xView_train.geojson')):
-      # Convert xView geoJSON labels to YOLO format
-      path = fname.parent
-      with open(fname) as f:
-          print(f'Loading {fname}...')
-          data = json.load(f)
-
-      # Make dirs
-      labels = Path(path / 'labels' / 'train')
-      os.system(f'rm -rf {labels}')
-      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']:
-              id = p['image_id']
-              file = path / 'train_images' / id
-              if 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 0-60
-                      assert 59 >= cls >= 0, f'incorrect class index {cls}'
-
-                      # Write YOLO label
-                      if id not in shapes:
-                          shapes[id] = Image.open(file).size
-                      box = xyxy2xywhn(box[None].astype(np.float), w=shapes[id][0], h=shapes[id][1], clip=True)
-                      with open((labels / id).with_suffix('.txt'), 'a') 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 {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')

ultralytics/cfg/default.yaml

@@ -10,14 +10,14 @@ data: # (str, optional) path to data file, i.e. coco128.yaml
 epochs: 100 # (int) number of epochs to train for
 time: # (float, optional) number of hours to train for, overrides epochs if supplied
 patience: 100 # (int) epochs to wait for no observable improvement for early stopping of training
-batch: 16 # (int) number of images per batch (-1 for AutoBatch)
+batch: 8 # (int) number of images per batch (-1 for AutoBatch)
 imgsz: 640 # (int | list) input images size as int for train and val modes, or list[w,h] for predict and export modes
 save: True # (bool) save train checkpoints and predict results
 save_period: -1 # (int) Save checkpoint every x epochs (disabled if < 1)
 val_period: 1 # (int) Validation every x epochs
 cache: False # (bool) True/ram, disk or False. Use cache for data loading
 device: # (int | str | list, optional) device to run on, i.e. cuda device=0 or device=0,1,2,3 or device=cpu
-workers: 8 # (int) number of worker threads for data loading (per RANK if DDP)
+workers: 2 # (int) number of worker threads for data loading (per RANK if DDP)
 project: # (str, optional) project name
 name: # (str, optional) experiment name, results saved to 'project/name' directory
 exist_ok: False # (bool) whether to overwrite existing experiment

ultralytics/cfg/models/v10/yolov10b-seg.yaml

@@ -0,0 +1,40 @@
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+  # [depth, width, max_channels]
+  b: [0.67, 1.00, 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, 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
+
+# YOLOv8.0n 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, v10Segment, [nc, 32, 256]] # segment(P3, P4, P5)

ultralytics/cfg/models/v10/yolov10l-seg.yaml

@@ -0,0 +1,40 @@
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+  # [depth, width, max_channels]
+  l: [1.00, 1.00, 512] # YOLOv8l summary: 365 layers, 43691520 parameters, 43691504 gradients, 165.7 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, 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
+
+# YOLOv8.0n 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, v10Segment, [nc, 32, 256]] # segment(P3, P4, P5)

ultralytics/cfg/models/v10/yolov10m-seg.yaml

@@ -0,0 +1,43 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+# YOLOv8 object detection model with P3-P5 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=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+  # [depth, width, max_channels]
+  m: [0.67, 0.75, 768] # YOLOv8m summary: 295 layers, 25902640 parameters, 25902624 gradients,  79.3 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, 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
+
+# YOLOv8.0n 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, v10Segment, [nc, 32, 256]] # segment(P3, P4, P5)

ultralytics/cfg/models/v10/yolov10n-seg.yaml

@@ -0,0 +1,40 @@
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+  # [depth, width, max_channels]
+  n: [0.33, 0.25, 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, 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
+
+# YOLOv8.0n 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, v10Segment, [nc, 32, 256]] # segment(P3, P4, P5)

ultralytics/cfg/models/v10/yolov10s-seg.yaml

@@ -0,0 +1,39 @@
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+  # [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
+
+# YOLOv8.0n 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, v10Segment, [nc, 32, 256]] # segment(P3, P4, P5)

ultralytics/cfg/models/v10/yolov10x-seg.yaml

@@ -0,0 +1,40 @@
+# Parameters
+nc: 80 # number of classes
+scales: # model compound scaling constants, i.e. 'model=yolov8n.yaml' will call yolov8.yaml with scale 'n'
+  # [depth, width, max_channels]
+  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, 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
+
+# YOLOv8.0n 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, v10Segment, [nc, 32, 256]] # segment(P3, P4, P5)

ultralytics/data/base.py

@@ -267,7 +267,7 @@ class BaseDataset(Dataset):
 
     def __len__(self):
         """Returns the length of the labels list for the dataset."""
-        return len(self.labels)
+        return int(0.1*len(self.labels))
 
     def update_labels_info(self, label):
         """Custom your label format here."""

ultralytics/engine/trainer.py

@@ -268,7 +268,7 @@ class BaseTrainer:
         self.amp = torch.tensor(self.args.amp).to(self.device)  # True or False
         if self.amp and RANK in (-1, 0):  # Single-GPU and DDP
             callbacks_backup = callbacks.default_callbacks.copy()  # backup callbacks as check_amp() resets them
-            self.amp = torch.tensor(check_amp(self.model), device=self.device)
+            self.amp = True# torch.tensor(check_amp(self.model), device=self.device)
             callbacks.default_callbacks = callbacks_backup  # restore callbacks
         if RANK > -1 and world_size > 1:  # DDP
             dist.broadcast(self.amp, src=0)  # broadcast the tensor from rank 0 to all other ranks (returns None)
@@ -420,6 +420,7 @@ class BaseTrainer:
 
             self.lr = {f"lr/pg{ir}": x["lr"] for ir, x in enumerate(self.optimizer.param_groups)}  # for loggers
             self.run_callbacks("on_train_epoch_end")
+            # validate
             if RANK in (-1, 0):
                 final_epoch = epoch + 1 == self.epochs
                 self.ema.update_attr(self.model, include=["yaml", "nc", "args", "names", "stride", "class_weights"])

ultralytics/engine/validator.py

@@ -187,7 +187,7 @@ class BaseValidator:
                 preds = self.postprocess(preds)
 
             self.update_metrics(preds, batch)
-            if self.args.plots and batch_i < 3:
+            if False:#self.args.plots and batch_i < 3:
                 self.plot_val_samples(batch, batch_i)
                 self.plot_predictions(batch, preds, batch_i)
 

ultralytics/models/__init__.py

@@ -4,5 +4,5 @@ from .rtdetr import RTDETR
 from .sam import SAM
 from .yolo import YOLO, YOLOWorld
 from .yolov10 import YOLOv10
-
+from .yolov10seg import YOLOv10Seg
-__all__ = "YOLO", "RTDETR", "SAM", "YOLOWorld", "YOLOv10"  # allow simpler import
+__all__ = "YOLO", "RTDETR", "SAM", "YOLOWorld", "YOLOv10","YOLOv10Seg"  # allow simpler import

ultralytics/models/yolov10/model.py

@@ -7,7 +7,7 @@ from .train import YOLOv10DetectionTrainer
 from huggingface_hub import PyTorchModelHubMixin
 from .card import card_template_text
 
-class YOLOv10(Model, PyTorchModelHubMixin, model_card_template=card_template_text):
+class YOLOv10(Model):# , PyTorchModelHubMixin, model_card_template=card_template_text):
 
     def __init__(self, model="yolov10n.pt", task=None, verbose=False, 
                  names=None):
@@ -33,4 +33,6 @@ class YOLOv10(Model, PyTorchModelHubMixin, model_card_template=card_template_tex
                 "validator": YOLOv10DetectionValidator,
                 "predictor": YOLOv10DetectionPredictor,
             },
-        }
+        }
+    
+

ultralytics/models/yolov10seg/__init__.py

@@ -0,0 +1,5 @@
+from .model import YOLOv10Seg
+from .predict import YOLOv10SegPredictor
+from .val import YOLOv10SegValidator
+
+__all__ = "YOLOv10DetectionPredictor", "YOLOv10DetectionValidator", "YOLOv10Seg"

ultralytics/models/yolov10seg/card.py

@@ -0,0 +1,64 @@
+card_template_text = """
+---
+license: agpl-3.0
+library_name: ultralytics
+repo_url: https://github.com/THU-MIG/yolov10
+tags:
+- object-detection
+- computer-vision
+- yolov10
+datasets:
+- detection-datasets/coco
+inference: false
+---
+
+### Model Description
+[YOLOv10: Real-Time End-to-End Object Detection](https://arxiv.org/abs/2405.14458v1)
+
+- arXiv: https://arxiv.org/abs/2405.14458v1
+- github: https://github.com/THU-MIG/yolov10
+
+### Installation
+```
+pip install git+https://github.com/THU-MIG/yolov10.git
+```
+
+### Training and validation
+```python
+from ultralytics import YOLOv10
+
+model = YOLOv10.from_pretrained('jameslahm/yolov10n')
+# Training
+model.train(...)
+# after training, one can push to the hub
+model.push_to_hub("your-hf-username/yolov10-finetuned")
+
+# Validation
+model.val(...)
+```
+
+### Inference
+
+Here's an end-to-end example showcasing inference on a cats image:
+
+```python
+from ultralytics import YOLOv10
+
+model = YOLOv10.from_pretrained('jameslahm/yolov10n')
+source = 'http://images.cocodataset.org/val2017/000000039769.jpg'
+model.predict(source=source, save=True)
+```
+which shows:
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/628ece6054698ce61d1e7be3/tBwAsKcQA_96HCYQp7BRr.png)
+
+### BibTeX Entry and Citation Info
+```
+@article{wang2024yolov10,
+  title={YOLOv10: Real-Time End-to-End Object Detection},
+  author={Wang, Ao and Chen, Hui and Liu, Lihao and Chen, Kai and Lin, Zijia and Han, Jungong and Ding, Guiguang},
+  journal={arXiv preprint arXiv:2405.14458},
+  year={2024}
+}
+```
+""".strip()

ultralytics/models/yolov10seg/model.py

@@ -0,0 +1,36 @@
+from ultralytics.engine.model import Model
+from ultralytics.nn.tasks import YOLOv10SegmentationModel
+from .val import YOLOv10SegValidator
+from .predict import YOLOv10SegPredictor
+from .train import YOLOv10SegTrainer
+
+from huggingface_hub import PyTorchModelHubMixin
+from .card import card_template_text
+
+class YOLOv10Seg(Model):# , PyTorchModelHubMixin, model_card_template=card_template_text):
+
+    def __init__(self, model="yolov10n.pt", task=None, verbose=False, 
+                 names=None):
+        super().__init__(model=model, task=task, verbose=verbose)
+        if names is not None:
+            setattr(self.model, 'names', names)
+
+    def push_to_hub(self, repo_name, **kwargs):
+        config = kwargs.get('config', {})
+        config['names'] = self.names
+        config['model'] = self.model.yaml['yaml_file']
+        config['task'] = self.task
+        kwargs['config'] = config
+        super().push_to_hub(repo_name, **kwargs)
+
+    @property
+    def task_map(self):
+        """Map head to model, trainer, validator, and predictor classes."""
+        return {
+            "segment": {
+                "model": YOLOv10SegmentationModel,
+                "trainer": YOLOv10SegTrainer,
+                "validator": YOLOv10SegValidator,
+                "predictor": YOLOv10SegPredictor,
+            },
+        }

ultralytics/models/yolov10seg/predict.py

@@ -0,0 +1,45 @@
+from ultralytics.models.yolo.detect import DetectionPredictor
+import torch
+from ultralytics.utils import ops
+from ultralytics.engine.results import Results
+import torch.nn.functional as F
+
+class YOLOv10SegPredictor(DetectionPredictor):
+    def postprocess(self, preds, img, orig_imgs):
+        coef,proto = None,None
+        if isinstance(preds, dict):
+            coef = preds['coef']
+            proto = preds['proto']
+            preds = preds["one2one"]
+        if isinstance(preds, (list, tuple)):
+            preds = preds[0]  # [1,5,6006]  coef[1,32,6006]  proto[1,32,104,176]
+
+        if preds.shape[-1] == 6:
+            pass
+        else:
+            preds = preds.transpose(-1, -2)  # [1,6006,5]
+            coef = coef.transpose(-1, -2)
+            # bboxes, scores, labels = ops.v10postprocess(preds, self.args.max_det, preds.shape[-1]-4)
+            bboxes, scores, labels,segmask = ops.v10segpostprocess([preds,coef,proto], self.args.max_det, preds.shape[-1]-4)
+            bboxes = ops.xywh2xyxy(bboxes)
+            preds = torch.cat([bboxes, scores.unsqueeze(-1), labels.unsqueeze(-1)], dim=-1)
+        mask = preds[..., 4] > self.args.conf
+        if self.args.classes is not None:
+            mask = mask & (preds[..., 5:6] == torch.tensor(self.args.classes, device=preds.device).unsqueeze(0)).any(2)
+        
+        preds = [p[mask[idx]] for idx, p in enumerate(preds)]
+        segmask = [p[mask[idx]] for idx, p in enumerate(segmask)]
+        if not isinstance(orig_imgs, list):  # input images are a torch.Tensor, not a list
+            orig_imgs = ops.convert_torch2numpy_batch(orig_imgs)
+
+        results = []
+        for i, pred in enumerate(preds):
+            orig_img = orig_imgs[i]
+            seg = segmask[i]
+            cc,hh,ww = seg.shape
+            seg = F.interpolate(seg[None], (hh*4, ww*4), mode="bilinear", align_corners=False)[0].gt_(0)            
+            pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape)
+            
+            img_path = self.batch[0][i]
+            results.append(Results(orig_img, path=img_path, names=self.model.names, boxes=pred,masks=seg))
+        return results

ultralytics/models/yolov10seg/train.py

@@ -0,0 +1,20 @@
+from ultralytics.models.yolo.detect import DetectionTrainer
+from .val import YOLOv10SegValidator
+from .model import YOLOv10SegmentationModel
+from copy import copy
+from ultralytics.utils import RANK
+
+class YOLOv10SegTrainer(DetectionTrainer):
+    def get_validator(self):
+        """Returns a DetectionValidator for YOLO model validation."""
+        self.loss_names = "box_om", "cls_om", "dfl_om", "box_oo", "cls_oo", "dfl_oo", 
+        return YOLOv10SegValidator(
+            self.test_loader, save_dir=self.save_dir, args=copy(self.args), _callbacks=self.callbacks
+        )
+
+    def get_model(self, cfg=None, weights=None, verbose=True):
+        """Return a YOLO detection model."""
+        model = YOLOv10SegmentationModel(cfg, nc=self.data["nc"], verbose=verbose and RANK == -1)
+        if weights:
+            model.load(weights)
+        return model

ultralytics/models/yolov10seg/val.py

@@ -0,0 +1,226 @@
+from ultralytics.models.yolo.detect import DetectionValidator
+from ultralytics.utils import ops
+import torch
+from ultralytics.utils.metrics import SegmentMetrics, box_iou, mask_iou
+import torch.nn.functional as F
+class YOLOv10SegValidator(DetectionValidator):
+    def __init__(self, dataloader=None, save_dir=None, pbar=None, args=None, _callbacks=None):
+        super().__init__(dataloader, save_dir, pbar, args, _callbacks)
+        self.args.save_json |= self.is_coco
+        self.plot_masks = None
+        self.process = None
+        self.args.task = "segment"
+        self.metrics = SegmentMetrics(save_dir=self.save_dir, on_plot=self.on_plot)
+    def init_metrics(self, model):
+        """Initialize metrics and select mask processing function based on save_json flag."""
+        super().init_metrics(model)
+        self.plot_masks = []
+        if self.args.save_json:
+            # check_requirements("pycocotools>=2.0.6")
+            self.process = ops.process_mask_upsample  # more accurate
+        else:
+            self.process = ops.process_mask  # faster
+        self.stats = dict(tp_m=[], tp=[], conf=[], pred_cls=[], target_cls=[])
+    def get_desc(self):
+        """Return a formatted description of evaluation metrics."""
+        return ("%22s" + "%11s" * 10) % (
+            "Class",
+            "Images",
+            "Instances",
+            "Box(P",
+            "R",
+            "mAP50",
+            "mAP50-95)",
+            "Mask(P",
+            "R",
+            "mAP50",
+            "mAP50-95)",
+        ) 
+    def _prepare_batch(self, si, batch):
+        """Prepares a batch for training or inference by processing images and targets."""
+        prepared_batch = super()._prepare_batch(si, batch)
+        midx = [si] if self.args.overlap_mask else batch["batch_idx"] == si
+        prepared_batch["masks"] = batch["masks"][midx]
+        return prepared_batch
+    
+    def finalize_metrics(self, *args, **kwargs):
+        """Sets speed and confusion matrix for evaluation metrics."""
+        self.metrics.speed = self.speed
+        self.metrics.confusion_matrix = self.confusion_matrix
+    def preprocess(self, batch):
+        """Preprocesses batch by converting masks to float and sending to device."""
+        batch = super().preprocess(batch)
+        batch["masks"] = batch["masks"].to(self.device).float()
+        return batch
+    def postprocess(self, preds):
+        coef,proto = None,None
+        if isinstance(preds, dict):
+            coef = preds["coef"]  # [1,32,5294]
+            proto = preds["proto"]  # [1,32,92,168]
+            preds = preds["one2one"]
+                
+        if isinstance(preds, (list, tuple)):
+            preds = preds[0]
+        
+        # Acknowledgement: Thanks to sanha9999 in #190 and #181!
+        if preds.shape[-1] == 6:
+            return preds
+        else:
+            preds = preds.transpose(-1, -2)  # [1,6006,5]
+            coef = coef.transpose(-1, -2)
+            # bboxes, scores, labels = ops.v10postprocess(preds, self.args.max_det, preds.shape[-1]-4)
+            bboxes, scores, labels,segmask = ops.v10segpostprocess([preds,coef,proto], self.args.max_det, preds.shape[-1]-4)
+            bboxes = ops.xywh2xyxy(bboxes)
+            preds = torch.cat([bboxes, scores.unsqueeze(-1), labels.unsqueeze(-1)], dim=-1)
+            return [preds,segmask]
+    def process_mask(self,segmask, bboxes, shape, upsample=False):
+        c, mh, mw = segmask.shape  # CHW
+        ih, iw = shape
+        width_ratio = mw / iw
+        height_ratio = mh / ih
+
+        downsampled_bboxes = bboxes.clone()
+        downsampled_bboxes[:, 0] *= width_ratio
+        downsampled_bboxes[:, 2] *= width_ratio
+        downsampled_bboxes[:, 3] *= height_ratio
+        downsampled_bboxes[:, 1] *= height_ratio
+
+        segmask = ops.crop_mask(segmask, downsampled_bboxes)  # CHW
+        if upsample:
+            segmask = F.interpolate(segmask[None], shape, mode="bilinear", align_corners=False)[0]  # CHW
+        return segmask.gt_(0)
+    
+    def _prepare_pred(self, inputx, pbatch):
+        """Prepares a batch for training or inference by processing images and targets."""
+        pred, pred_masks = None,None
+        if isinstance(inputx,list):
+            pred, pred_masks = inputx
+        else:
+            print("error!!!!!!!")
+        predn = pred.clone()
+        predn[:, :4] = ops.scale_boxes(
+            pbatch["imgsz"], predn[:, :4], pbatch["ori_shape"], ratio_pad=pbatch["ratio_pad"]
+        )  # native-space pred
+        pred_masks = self.process_mask(pred_masks, pred[:, :4], pbatch["imgsz"])
+        return predn, pred_masks
+    
+    def _process_batch(self, detections, gt_bboxes, gt_cls, pred_masks=None, gt_masks=None, overlap=False, masks=False):
+        """
+        Return correct prediction matrix.
+
+        Args:
+            detections (array[N, 6]), x1, y1, x2, y2, conf, class
+            labels (array[M, 5]), class, x1, y1, x2, y2
+
+        Returns:
+            correct (array[N, 10]), for 10 IoU levels
+        """
+        if masks:
+            if overlap:
+                nl = len(gt_cls)
+                index = torch.arange(nl, device=gt_masks.device).view(nl, 1, 1) + 1
+                gt_masks = gt_masks.repeat(nl, 1, 1)  # shape(1,640,640) -> (n,640,640)
+                gt_masks = torch.where(gt_masks == index, 1.0, 0.0)
+            if gt_masks.shape[1:] != pred_masks.shape[1:]:
+                gt_masks = F.interpolate(gt_masks[None], pred_masks.shape[1:], mode="bilinear", align_corners=False)[0]
+                gt_masks = gt_masks.gt_(0.5)
+            iou = mask_iou(gt_masks.view(gt_masks.shape[0], -1), pred_masks.view(pred_masks.shape[0], -1))
+        else:  # boxes
+            iou = box_iou(gt_bboxes, detections[:, :4])
+
+        return self.match_predictions(detections[:, 5], gt_cls, iou)
+    def update_metrics(self, preds, batch):
+        """Metrics."""
+        # box + score + label
+        # preds  [[1,300,6],[1,300,96,168]]
+        for si, (pred, pred_masks) in enumerate(zip(preds[0], preds[1])):
+            self.seen += 1
+            npr = len(pred)  # 300
+            stat = dict(
+                conf=torch.zeros(0, device=self.device),
+                pred_cls=torch.zeros(0, device=self.device),
+                tp=torch.zeros(npr, self.niou, dtype=torch.bool, device=self.device),
+                tp_m=torch.zeros(npr, self.niou, dtype=torch.bool, device=self.device),
+            )
+            pbatch = self._prepare_batch(si, batch)
+            cls, bbox = pbatch.pop("cls"), pbatch.pop("bbox")
+            nl = len(cls)
+            stat["target_cls"] = cls
+            if npr == 0:
+                if nl:
+                    for k in self.stats.keys():
+                        self.stats[k].append(stat[k])
+                    if self.args.plots:
+                        self.confusion_matrix.process_batch(detections=None, gt_bboxes=bbox, gt_cls=cls)
+                continue
+
+            # Masks
+            gt_masks = pbatch.pop("masks")
+            # Predictions
+            if self.args.single_cls:
+                pred[:, 5] = 0
+            predn,pred_masks = self._prepare_pred([pred,pred_masks], pbatch)
+
+            stat["conf"] = predn[:, 4]
+            stat["pred_cls"] = predn[:, 5]
+
+            # Evaluate
+            if nl:
+                stat["tp"] = self._process_batch(predn, bbox, cls)
+                stat["tp_m"] = self._process_batch(
+                    predn, bbox, cls, pred_masks, gt_masks, self.args.overlap_mask, masks=True
+                )
+                if self.args.plots:
+                    self.confusion_matrix.process_batch(predn, bbox, cls)
+
+            for k in self.stats.keys():
+                self.stats[k].append(stat[k])
+
+            pred_masks = torch.as_tensor(pred_masks, dtype=torch.uint8)
+            if self.args.plots and self.batch_i < 3:
+                self.plot_masks.append(pred_masks[:15].cpu())  # filter top 15 to plot
+
+            # Save
+            if False:# self.args.save_json:
+                pred_masks = ops.scale_image(
+                    pred_masks.permute(1, 2, 0).contiguous().cpu().numpy(),
+                    pbatch["ori_shape"],
+                    ratio_pad=batch["ratio_pad"][si],
+                )
+                self.pred_to_json(predn, batch["im_file"][si], pred_masks)
+                
+"""class YOLOv10SegValidator(DetectionValidator):
+   
+    def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None):
+        if overrides is None:
+            overrides = {}
+        overrides["task"] = "segment"
+        super().__init__(cfg, overrides, _callbacks)
+
+    def get_model(self, cfg=None, weights=None, verbose=True):
+        model = SegmentationModel(cfg, ch=3, nc=self.data["nc"], verbose=verbose and RANK == -1)
+        if weights:
+            model.load(weights)
+
+        return model
+
+    def get_validator(self):
+        self.loss_names = "box_loss", "seg_loss", "cls_loss", "dfl_loss"
+        return yolo.segment.SegmentationValidator(
+            self.test_loader, save_dir=self.save_dir, args=copy(self.args), _callbacks=self.callbacks
+        )
+
+    def plot_training_samples(self, batch, ni):
+        plot_images(
+            batch["img"],
+            batch["batch_idx"],
+            batch["cls"].squeeze(-1),
+            batch["bboxes"],
+            masks=batch["masks"],
+            paths=batch["im_file"],
+            fname=self.save_dir / f"train_batch{ni}.jpg",
+            on_plot=self.on_plot,
+        )
+
+    def plot_metrics(self):
+        plot_results(file=self.csv, segment=True, on_plot=self.on_plot)  # save results.png"""

ultralytics/nn/modules/__init__.py

@@ -66,7 +66,7 @@ from .conv import (
     RepConv,
     SpatialAttention,
 )
-from .head import OBB, Classify, Detect, Pose, RTDETRDecoder, Segment, WorldDetect, v10Detect
+from .head import OBB, Classify, Detect, Pose, RTDETRDecoder, Segment, WorldDetect, v10Detect,v10Segment
 from .transformer import (
     AIFI,
     MLP,
@@ -143,5 +143,6 @@ __all__ = (
     "C2fCIB",
     "SCDown",
     "RepVGGDW",
-    "v10Detect"
+    "v10Detect",
+    "v10Segment"
 )

ultralytics/nn/modules/head.py

@@ -494,8 +494,8 @@ class RTDETRDecoder(nn.Module):
         for layer in self.input_proj:
             xavier_uniform_(layer[0].weight)
 
-class v10Detect(Detect):
 
+class v10Detect(Detect):
     max_det = 300
 
     def __init__(self, nc=80, ch=()):
@@ -515,13 +515,13 @@ class v10Detect(Detect):
 
         if not self.training:
             one2one = self.inference(one2one)
-            if not self.export:
+            if not self.export:  
                 return {"one2many": one2many, "one2one": one2one}
-            else:
+            else: 
                 assert(self.max_det != -1)
                 boxes, scores, labels = ops.v10postprocess(one2one.permute(0, 2, 1), self.max_det, self.nc)
                 return torch.cat([boxes, scores.unsqueeze(-1), labels.unsqueeze(-1).to(boxes.dtype)], dim=-1)
-        else:
+        else: 
             return {"one2many": one2many, "one2one": one2one}
 
     def bias_init(self):
@@ -533,3 +533,39 @@ class v10Detect(Detect):
         for a, b, s in zip(m.one2one_cv2, m.one2one_cv3, m.stride):  # from
             a[-1].bias.data[:] = 1.0  # box
             b[-1].bias.data[: m.nc] = math.log(5 / m.nc / (640 / s) ** 2)  # cls (.01 objects, 80 classes, 640 img)
+
+class v10Segment(v10Detect):
+
+    def __init__(self, nc=80,nm=32, npr=256,ch=()):
+        super().__init__(nc, ch)
+        # seg
+        self.nm = nm
+        self.npr = npr
+        self.proto = Proto(ch[0], self.npr, self.nm)  # protos
+        self.detect = v10Detect.forward
+        c4 = max(ch[0] // 4, self.nm)
+        self.cv4 = nn.ModuleList(nn.Sequential(Conv(x, c4, 3), Conv(c4, c4, 3), nn.Conv2d(c4, self.nm, 1)) for x in ch)
+     
+    
+    def forward(self, x):
+        p = self.proto(x[0])  # mask protos
+        bs = p.shape[0]  # batch size
+        # mask coefficients
+        mc = torch.cat([self.cv4[i](x[i]).view(bs, self.nm, -1) for i in range(self.nl)], 2)  
+        x = self.detect(self, x)
+        # if self.training:
+        #     return x, mc, p
+        # return (torch.cat([x, mc], 1), p) if self.export else (torch.cat([x[0], mc], 1), (x[1], mc, p))
+        
+        if not self.training:
+            if not self.export:  # 验证
+                x["coef"] = mc
+                x["proto"] = p
+                return x
+                # return {"one2many": one2many, "one2one": one2one,"coef":mc, "proto":p}
+            else:  # 导出onnx
+                return x,mc,p
+        else:  # 训练
+            x["coef"] = mc
+            x["proto"] = p
+            return x # {"one2many": one2many, "one2one": one2one,"coef":mc, "proto":p}

ultralytics/nn/tasks.py

@@ -53,11 +53,12 @@ from ultralytics.nn.modules import (
     PSA,
     SCDown,
     RepVGGDW,
-    v10Detect
+    v10Detect,
+    v10Segment
 )
 from ultralytics.utils import DEFAULT_CFG_DICT, DEFAULT_CFG_KEYS, LOGGER, colorstr, emojis, yaml_load
 from ultralytics.utils.checks import check_requirements, check_suffix, check_yaml
-from ultralytics.utils.loss import v8ClassificationLoss, v8DetectionLoss, v8OBBLoss, v8PoseLoss, v8SegmentationLoss, v10DetectLoss
+from ultralytics.utils.loss import v8ClassificationLoss, v8DetectionLoss, v8OBBLoss, v8PoseLoss, v8SegmentationLoss, v10DetectLoss,v10SegmentationLoss
 from ultralytics.utils.plotting import feature_visualization
 from ultralytics.utils.torch_utils import (
     fuse_conv_and_bn,
@@ -303,7 +304,9 @@ class DetectionModel(BaseModel):
             m.inplace = self.inplace
             forward = lambda x: self.forward(x)[0] if isinstance(m, (Segment, Pose, OBB)) else self.forward(x)
             if isinstance(m, v10Detect):
-                forward = lambda x: self.forward(x)["one2many"]
+                forward = lambda x: self.forward(x)["one2many"] if isinstance(m, (v10Segment)) else self.forward(x)["one2many"]
+                # forward = lambda x: self.forward(x)["one2many"]
+            
             m.stride = torch.tensor([s / x.shape[-2] for x in forward(torch.zeros(1, ch, s, s))])  # forward
             self.stride = m.stride
             m.bias_init()  # only run once
@@ -645,6 +648,16 @@ class YOLOv10DetectionModel(DetectionModel):
     def init_criterion(self):
         return v10DetectLoss(self)
 
+
+class YOLOv10SegmentationModel(DetectionModel):
+    def __init__(self, cfg='yolov10n-seg.yaml', ch=3, nc=None, verbose=True):
+        """Initialize YOLOv8 segmentation model with given config and parameters."""
+        super().__init__(cfg=cfg, ch=ch, nc=nc, verbose=verbose)
+
+    def init_criterion(self):
+        return v10SegmentationLoss(self)
+        # return v10DetectLoss(self)
+
 class Ensemble(nn.ModuleList):
     """Ensemble of models."""
 
@@ -917,10 +930,11 @@ def parse_model(d, ch, verbose=True):  # model_dict, input_channels(3)
             args = [ch[f]]
         elif m is Concat:
             c2 = sum(ch[x] for x in f)
-        elif m in {Detect, WorldDetect, Segment, Pose, OBB, ImagePoolingAttn, v10Detect}:
+        elif m in {Detect, WorldDetect, Segment, Pose, OBB, ImagePoolingAttn, v10Detect,v10Segment}:
             args.append([ch[x] for x in f])
-            if m is Segment:
+            if m is Segment or m is v10Segment:
                 args[2] = make_divisible(min(args[2], max_channels) * width, 8)
+
         elif m is RTDETRDecoder:  # special case, channels arg must be passed in index 1
             args.insert(1, [ch[x] for x in f])
         elif m is CBLinear:
@@ -1007,7 +1021,7 @@ def guess_model_task(model):
             return "classify"
         if m == "detect" or m == "v10detect":
             return "detect"
-        if m == "segment":
+        if m == "segment" or m == "v10segment":
             return "segment"
         if m == "pose":
             return "pose"

ultralytics/utils/loss.py

@@ -191,6 +191,7 @@ class v8DetectionLoss:
             pred_dist = pred_dist.view(b, a, 4, c // 4).softmax(3).matmul(self.proj.type(pred_dist.dtype))
             # pred_dist = pred_dist.view(b, a, c // 4, 4).transpose(2,3).softmax(3).matmul(self.proj.type(pred_dist.dtype))
             # pred_dist = (pred_dist.view(b, a, c // 4, 4).softmax(2) * self.proj.type(pred_dist.dtype).view(1, 1, -1, 1)).sum(2)
+        
         return dist2bbox(pred_dist, anchor_points, xywh=False)
 
     def __call__(self, preds, batch):
@@ -250,15 +251,21 @@ class v8DetectionLoss:
 class v8SegmentationLoss(v8DetectionLoss):
     """Criterion class for computing training losses."""
 
-    def __init__(self, model):  # model must be de-paralleled
+    def __init__(self, model,tal_topk=10):  # model must be de-paralleled
         """Initializes the v8SegmentationLoss class, taking a de-paralleled model as argument."""
-        super().__init__(model)
+        super().__init__(model,tal_topk)
         self.overlap = model.args.overlap_mask
 
     def __call__(self, preds, batch):
         """Calculate and return the loss for the YOLO model."""
+
         loss = torch.zeros(4, device=self.device)  # box, cls, dfl
         feats, pred_masks, proto = preds if len(preds) == 3 else preds[1]
+        feats = feats[1] if isinstance(feats, tuple) else feats
+
+        # [4, 65, 80, 80] [4, 65, 40, 40] [4, 65, 20, 20]
+        # [4, 32, 8400] [4, 32, 160, 160]
+
         batch_size, _, mask_h, mask_w = proto.shape  # batch size, number of masks, mask height, mask width
         pred_distri, pred_scores = torch.cat([xi.view(feats[0].shape[0], self.no, -1) for xi in feats], 2).split(
             (self.reg_max * 4, self.nc), 1
@@ -288,7 +295,6 @@ class v8SegmentationLoss(v8DetectionLoss):
                 "correctly formatted 'segment' dataset using 'data=coco8-seg.yaml' "
                 "as an example.\nSee https://docs.ultralytics.com/datasets/segment/ for help."
             ) from e
-
         # Pboxes
         pred_bboxes = self.bbox_decode(anchor_points, pred_distri)  # xyxy, (b, h*w, 4)
 
@@ -725,3 +731,26 @@ class v10DetectLoss:
         one2one = preds["one2one"]
         loss_one2one = self.one2one(one2one, batch)
         return loss_one2many[0] + loss_one2one[0], torch.cat((loss_one2many[1], loss_one2one[1]))
+
+
+
+
+class v10SegmentationLoss:
+    """Criterion class for computing training losses."""
+
+    def __init__(self, model):  # model must be de-paralleled
+        """Initializes the v8SegmentationLoss class, taking a de-paralleled model as argument."""
+        self.overlap = model.args.overlap_mask
+        self.one2many = v8SegmentationLoss(model, tal_topk=10)
+        self.one2one = v8SegmentationLoss(model, tal_topk=1)
+        
+    def __call__(self, preds, batch):
+        """Calculate and return the loss for the YOLO model."""   
+        one2many = [preds["one2many"],preds["coef"],preds["proto"]]
+        loss_one2many = self.one2many(one2many, batch)
+        one2one = [preds["one2one"],preds["coef"],preds["proto"]]
+        loss_one2one = self.one2one(one2one, batch)
+        return loss_one2many[0] + loss_one2one[0], torch.cat((loss_one2many[1], loss_one2one[1]))
+
+
+    

ultralytics/utils/ops.py

@@ -851,7 +851,7 @@ def clean_str(s):
 def v10postprocess(preds, max_det, nc=80):
     assert(4 + nc == preds.shape[-1])
     boxes, scores = preds.split([4, nc], dim=-1)
-    max_scores = scores.amax(dim=-1)
+    max_scores = scores.amax(dim=-1)  
     max_scores, index = torch.topk(max_scores, max_det, dim=-1)
     index = index.unsqueeze(-1)
     boxes = torch.gather(boxes, dim=1, index=index.repeat(1, 1, boxes.shape[-1]))
@@ -861,4 +861,26 @@ def v10postprocess(preds, max_det, nc=80):
     labels = index % nc
     index = index // nc
     boxes = boxes.gather(dim=1, index=index.unsqueeze(-1).repeat(1, 1, boxes.shape[-1]))
-    return boxes, scores, labels
+    return boxes, scores, labels
+
+def v10segpostprocess(preds, max_det, nc=80):
+    proto,coef = None,None
+    proto_w,proto_h = 0,0
+    if isinstance(preds,list):
+        preds,coef,proto = preds  
+        batch,cc,proto_h,proto_w = proto.shape
+    assert(4 + nc == preds.shape[-1])
+    boxes, scores = preds.split([4, nc], dim=-1) 
+    max_scores = scores.amax(dim=-1) 
+    max_scores, index = torch.topk(max_scores, max_det, dim=-1)
+    index = index.unsqueeze(-1)  
+    boxes = torch.gather(boxes, dim=1, index=index.repeat(1, 1, boxes.shape[-1]))
+    scores = torch.gather(scores, dim=1, index=index.repeat(1, 1, scores.shape[-1]))
+    coef = torch.gather(coef, dim=1, index=index.repeat(1, 1, coef.shape[-1])) # [1,32,300]
+    segmask = torch.matmul(coef, proto.reshape(batch,cc,-1)).reshape(batch, max_det,proto_h,proto_w)
+    scores, index = torch.topk(scores.flatten(1), max_det, dim=-1)
+    labels = index % nc
+    index = index // nc
+    boxes = boxes.gather(dim=1, index=index.unsqueeze(-1).repeat(1, 1, boxes.shape[-1]))
+
+    return boxes, scores, labels,segmask

ultralytics/utils/tal.py

@@ -301,6 +301,7 @@ def make_anchors(feats, strides, grid_cell_offset=0.5):
         sx = torch.arange(end=w, device=device, dtype=dtype) + grid_cell_offset  # shift x
         sy = torch.arange(end=h, device=device, dtype=dtype) + grid_cell_offset  # shift y
         sy, sx = torch.meshgrid(sy, sx, indexing="ij") if TORCH_1_10 else torch.meshgrid(sy, sx)
+        # print("torch.stack((sx, sy), -1).view(-1, 2) = ",torch.stack((sx, sy), -1).view(-1, 2).shape)
         anchor_points.append(torch.stack((sx, sy), -1).view(-1, 2))
         stride_tensor.append(torch.full((h * w, 1), stride, dtype=dtype, device=device))
     return torch.cat(anchor_points), torch.cat(stride_tensor)