diff --git a/ultralytics/nn/autobackend.py b/ultralytics/nn/autobackend.py index 937c035..1bbecca 100644 --- a/ultralytics/nn/autobackend.py +++ b/ultralytics/nn/autobackend.py @@ -227,7 +227,7 @@ class AutoBackend(nn.Module): if 'names' not in locals(): names = yaml_load(data)['names'] if data else {i: f'class{i}' for i in range(999)} if names[0] == 'n01440764' and len(names) == 1000: # ImageNet - names = yaml_load(ROOT / 'data/ImageNet.yaml')['names'] # human-readable names + names = yaml_load(ROOT / 'yolo/data/datasets/ImageNet.yaml')['names'] # human-readable names self.__dict__.update(locals()) # assign all variables to self diff --git a/ultralytics/yolo/data/datasets/Argoverse.yaml b/ultralytics/yolo/data/datasets/Argoverse.yaml new file mode 100644 index 0000000..35896da --- /dev/null +++ b/ultralytics/yolo/data/datasets/Argoverse.yaml @@ -0,0 +1,74 @@ +# Ultralytics YOLO 🚀, GPL-3.0 license +# Argoverse-HD dataset (ring-front-center camera) http://www.cs.cmu.edu/~mengtial/proj/streaming/ by Argo AI +# Example usage: python train.py --data Argoverse.yaml +# parent +# ├── yolov5 +# └── datasets +# └── Argoverse ← downloads here (31.3 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/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 utils.general import download, 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 + dir = Path(yaml['path']) # dataset root dir + urls = ['https://argoverse-hd.s3.us-east-2.amazonaws.com/Argoverse-HD-Full.zip'] + download(urls, dir=dir, delete=False) + + # 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 VisDrone annotations to YOLO labels diff --git a/ultralytics/yolo/data/datasets/GlobalWheat2020.yaml b/ultralytics/yolo/data/datasets/GlobalWheat2020.yaml new file mode 100644 index 0000000..286a9bd --- /dev/null +++ b/ultralytics/yolo/data/datasets/GlobalWheat2020.yaml @@ -0,0 +1,54 @@ +# Ultralytics YOLO 🚀, GPL-3.0 license +# Global Wheat 2020 dataset http://www.global-wheat.com/ by University of Saskatchewan +# Example usage: python train.py --data GlobalWheat2020.yaml +# parent +# ├── yolov5 +# └── 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 utils.general import download, 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 / p).rename(dir / 'images' / p) # move to /images + f = (dir / p).with_suffix('.json') # json file + if f.exists(): + f.rename((dir / 'annotations' / p).with_suffix('.json')) # move to /annotations diff --git a/ultralytics/yolo/data/datasets/ImageNet.yaml b/ultralytics/yolo/data/datasets/ImageNet.yaml new file mode 100644 index 0000000..264d992 --- /dev/null +++ b/ultralytics/yolo/data/datasets/ImageNet.yaml @@ -0,0 +1,1022 @@ +# Ultralytics YOLO 🚀, GPL-3.0 license +# ImageNet-1k dataset https://www.image-net.org/index.php by Stanford University +# Simplified class names from https://github.com/anishathalye/imagenet-simple-labels +# Example usage: python classify/train.py --data imagenet +# parent +# ├── yolov5 +# └── datasets +# └── imagenet ← downloads here (144 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/imagenet # dataset root dir +train: train # train images (relative to 'path') 1281167 images +val: val # val images (relative to 'path') 50000 images +test: # test images (optional) + +# Classes +names: + 0: tench + 1: goldfish + 2: great white shark + 3: tiger shark + 4: hammerhead shark + 5: electric ray + 6: stingray + 7: cock + 8: hen + 9: ostrich + 10: brambling + 11: goldfinch + 12: house finch + 13: junco + 14: indigo bunting + 15: American robin + 16: bulbul + 17: jay + 18: magpie + 19: chickadee + 20: American dipper + 21: kite + 22: bald eagle + 23: vulture + 24: great grey owl + 25: fire salamander + 26: smooth newt + 27: newt + 28: spotted salamander + 29: axolotl + 30: American bullfrog + 31: tree frog + 32: tailed frog + 33: loggerhead sea turtle + 34: leatherback sea turtle + 35: mud turtle + 36: terrapin + 37: box turtle + 38: banded gecko + 39: green iguana + 40: Carolina anole + 41: desert grassland whiptail lizard + 42: agama + 43: frilled-necked lizard + 44: alligator lizard + 45: Gila monster + 46: European green lizard + 47: chameleon + 48: Komodo dragon + 49: Nile crocodile + 50: American alligator + 51: triceratops + 52: worm snake + 53: ring-necked snake + 54: eastern hog-nosed snake + 55: smooth green snake + 56: kingsnake + 57: garter snake + 58: water snake + 59: vine snake + 60: night snake + 61: boa constrictor + 62: African rock python + 63: Indian cobra + 64: green mamba + 65: sea snake + 66: Saharan horned viper + 67: eastern diamondback rattlesnake + 68: sidewinder + 69: trilobite + 70: harvestman + 71: scorpion + 72: yellow garden spider + 73: barn spider + 74: European garden spider + 75: southern black widow + 76: tarantula + 77: wolf spider + 78: tick + 79: centipede + 80: black grouse + 81: ptarmigan + 82: ruffed grouse + 83: prairie grouse + 84: peacock + 85: quail + 86: partridge + 87: grey parrot + 88: macaw + 89: sulphur-crested cockatoo + 90: lorikeet + 91: coucal + 92: bee eater + 93: hornbill + 94: hummingbird + 95: jacamar + 96: toucan + 97: duck + 98: red-breasted merganser + 99: goose + 100: black swan + 101: tusker + 102: echidna + 103: platypus + 104: wallaby + 105: koala + 106: wombat + 107: jellyfish + 108: sea anemone + 109: brain coral + 110: flatworm + 111: nematode + 112: conch + 113: snail + 114: slug + 115: sea slug + 116: chiton + 117: chambered nautilus + 118: Dungeness crab + 119: rock crab + 120: fiddler crab + 121: red king crab + 122: American lobster + 123: spiny lobster + 124: crayfish + 125: hermit crab + 126: isopod + 127: white stork + 128: black stork + 129: spoonbill + 130: flamingo + 131: little blue heron + 132: great egret + 133: bittern + 134: crane (bird) + 135: limpkin + 136: common gallinule + 137: American coot + 138: bustard + 139: ruddy turnstone + 140: dunlin + 141: common redshank + 142: dowitcher + 143: oystercatcher + 144: pelican + 145: king penguin + 146: albatross + 147: grey whale + 148: killer whale + 149: dugong + 150: sea lion + 151: Chihuahua + 152: Japanese Chin + 153: Maltese + 154: Pekingese + 155: Shih Tzu + 156: King Charles Spaniel + 157: Papillon + 158: toy terrier + 159: Rhodesian Ridgeback + 160: Afghan Hound + 161: Basset Hound + 162: Beagle + 163: Bloodhound + 164: Bluetick Coonhound + 165: Black and Tan Coonhound + 166: Treeing Walker Coonhound + 167: English foxhound + 168: Redbone Coonhound + 169: borzoi + 170: Irish Wolfhound + 171: Italian Greyhound + 172: Whippet + 173: Ibizan Hound + 174: Norwegian Elkhound + 175: Otterhound + 176: Saluki + 177: Scottish Deerhound + 178: Weimaraner + 179: Staffordshire Bull Terrier + 180: American Staffordshire Terrier + 181: Bedlington Terrier + 182: Border Terrier + 183: Kerry Blue Terrier + 184: Irish Terrier + 185: Norfolk Terrier + 186: Norwich Terrier + 187: Yorkshire Terrier + 188: Wire Fox Terrier + 189: Lakeland Terrier + 190: Sealyham Terrier + 191: Airedale Terrier + 192: Cairn Terrier + 193: Australian Terrier + 194: Dandie Dinmont Terrier + 195: Boston Terrier + 196: Miniature Schnauzer + 197: Giant Schnauzer + 198: Standard Schnauzer + 199: Scottish Terrier + 200: Tibetan Terrier + 201: Australian Silky Terrier + 202: Soft-coated Wheaten Terrier + 203: West Highland White Terrier + 204: Lhasa Apso + 205: Flat-Coated Retriever + 206: Curly-coated Retriever + 207: Golden Retriever + 208: Labrador Retriever + 209: Chesapeake Bay Retriever + 210: German Shorthaired Pointer + 211: Vizsla + 212: English Setter + 213: Irish Setter + 214: Gordon Setter + 215: Brittany + 216: Clumber Spaniel + 217: English Springer Spaniel + 218: Welsh Springer Spaniel + 219: Cocker Spaniels + 220: Sussex Spaniel + 221: Irish Water Spaniel + 222: Kuvasz + 223: Schipperke + 224: Groenendael + 225: Malinois + 226: Briard + 227: Australian Kelpie + 228: Komondor + 229: Old English Sheepdog + 230: Shetland Sheepdog + 231: collie + 232: Border Collie + 233: Bouvier des Flandres + 234: Rottweiler + 235: German Shepherd Dog + 236: Dobermann + 237: Miniature Pinscher + 238: Greater Swiss Mountain Dog + 239: Bernese Mountain Dog + 240: Appenzeller Sennenhund + 241: Entlebucher Sennenhund + 242: Boxer + 243: Bullmastiff + 244: Tibetan Mastiff + 245: French Bulldog + 246: Great Dane + 247: St. Bernard + 248: husky + 249: Alaskan Malamute + 250: Siberian Husky + 251: Dalmatian + 252: Affenpinscher + 253: Basenji + 254: pug + 255: Leonberger + 256: Newfoundland + 257: Pyrenean Mountain Dog + 258: Samoyed + 259: Pomeranian + 260: Chow Chow + 261: Keeshond + 262: Griffon Bruxellois + 263: Pembroke Welsh Corgi + 264: Cardigan Welsh Corgi + 265: Toy Poodle + 266: Miniature Poodle + 267: Standard Poodle + 268: Mexican hairless dog + 269: grey wolf + 270: Alaskan tundra wolf + 271: red wolf + 272: coyote + 273: dingo + 274: dhole + 275: African wild dog + 276: hyena + 277: red fox + 278: kit fox + 279: Arctic fox + 280: grey fox + 281: tabby cat + 282: tiger cat + 283: Persian cat + 284: Siamese cat + 285: Egyptian Mau + 286: cougar + 287: lynx + 288: leopard + 289: snow leopard + 290: jaguar + 291: lion + 292: tiger + 293: cheetah + 294: brown bear + 295: American black bear + 296: polar bear + 297: sloth bear + 298: mongoose + 299: meerkat + 300: tiger beetle + 301: ladybug + 302: ground beetle + 303: longhorn beetle + 304: leaf beetle + 305: dung beetle + 306: rhinoceros beetle + 307: weevil + 308: fly + 309: bee + 310: ant + 311: grasshopper + 312: cricket + 313: stick insect + 314: cockroach + 315: mantis + 316: cicada + 317: leafhopper + 318: lacewing + 319: dragonfly + 320: damselfly + 321: red admiral + 322: ringlet + 323: monarch butterfly + 324: small white + 325: sulphur butterfly + 326: gossamer-winged butterfly + 327: starfish + 328: sea urchin + 329: sea cucumber + 330: cottontail rabbit + 331: hare + 332: Angora rabbit + 333: hamster + 334: porcupine + 335: fox squirrel + 336: marmot + 337: beaver + 338: guinea pig + 339: common sorrel + 340: zebra + 341: pig + 342: wild boar + 343: warthog + 344: hippopotamus + 345: ox + 346: water buffalo + 347: bison + 348: ram + 349: bighorn sheep + 350: Alpine ibex + 351: hartebeest + 352: impala + 353: gazelle + 354: dromedary + 355: llama + 356: weasel + 357: mink + 358: European polecat + 359: black-footed ferret + 360: otter + 361: skunk + 362: badger + 363: armadillo + 364: three-toed sloth + 365: orangutan + 366: gorilla + 367: chimpanzee + 368: gibbon + 369: siamang + 370: guenon + 371: patas monkey + 372: baboon + 373: macaque + 374: langur + 375: black-and-white colobus + 376: proboscis monkey + 377: marmoset + 378: white-headed capuchin + 379: howler monkey + 380: titi + 381: Geoffroy's spider monkey + 382: common squirrel monkey + 383: ring-tailed lemur + 384: indri + 385: Asian elephant + 386: African bush elephant + 387: red panda + 388: giant panda + 389: snoek + 390: eel + 391: coho salmon + 392: rock beauty + 393: clownfish + 394: sturgeon + 395: garfish + 396: lionfish + 397: pufferfish + 398: abacus + 399: abaya + 400: academic gown + 401: accordion + 402: acoustic guitar + 403: aircraft carrier + 404: airliner + 405: airship + 406: altar + 407: ambulance + 408: amphibious vehicle + 409: analog clock + 410: apiary + 411: apron + 412: waste container + 413: assault rifle + 414: backpack + 415: bakery + 416: balance beam + 417: balloon + 418: ballpoint pen + 419: Band-Aid + 420: banjo + 421: baluster + 422: barbell + 423: barber chair + 424: barbershop + 425: barn + 426: barometer + 427: barrel + 428: wheelbarrow + 429: baseball + 430: basketball + 431: bassinet + 432: bassoon + 433: swimming cap + 434: bath towel + 435: bathtub + 436: station wagon + 437: lighthouse + 438: beaker + 439: military cap + 440: beer bottle + 441: beer glass + 442: bell-cot + 443: bib + 444: tandem bicycle + 445: bikini + 446: ring binder + 447: binoculars + 448: birdhouse + 449: boathouse + 450: bobsleigh + 451: bolo tie + 452: poke bonnet + 453: bookcase + 454: bookstore + 455: bottle cap + 456: bow + 457: bow tie + 458: brass + 459: bra + 460: breakwater + 461: breastplate + 462: broom + 463: bucket + 464: buckle + 465: bulletproof vest + 466: high-speed train + 467: butcher shop + 468: taxicab + 469: cauldron + 470: candle + 471: cannon + 472: canoe + 473: can opener + 474: cardigan + 475: car mirror + 476: carousel + 477: tool kit + 478: carton + 479: car wheel + 480: automated teller machine + 481: cassette + 482: cassette player + 483: castle + 484: catamaran + 485: CD player + 486: cello + 487: mobile phone + 488: chain + 489: chain-link fence + 490: chain mail + 491: chainsaw + 492: chest + 493: chiffonier + 494: chime + 495: china cabinet + 496: Christmas stocking + 497: church + 498: movie theater + 499: cleaver + 500: cliff dwelling + 501: cloak + 502: clogs + 503: cocktail shaker + 504: coffee mug + 505: coffeemaker + 506: coil + 507: combination lock + 508: computer keyboard + 509: confectionery store + 510: container ship + 511: convertible + 512: corkscrew + 513: cornet + 514: cowboy boot + 515: cowboy hat + 516: cradle + 517: crane (machine) + 518: crash helmet + 519: crate + 520: infant bed + 521: Crock Pot + 522: croquet ball + 523: crutch + 524: cuirass + 525: dam + 526: desk + 527: desktop computer + 528: rotary dial telephone + 529: diaper + 530: digital clock + 531: digital watch + 532: dining table + 533: dishcloth + 534: dishwasher + 535: disc brake + 536: dock + 537: dog sled + 538: dome + 539: doormat + 540: drilling rig + 541: drum + 542: drumstick + 543: dumbbell + 544: Dutch oven + 545: electric fan + 546: electric guitar + 547: electric locomotive + 548: entertainment center + 549: envelope + 550: espresso machine + 551: face powder + 552: feather boa + 553: filing cabinet + 554: fireboat + 555: fire engine + 556: fire screen sheet + 557: flagpole + 558: flute + 559: folding chair + 560: football helmet + 561: forklift + 562: fountain + 563: fountain pen + 564: four-poster bed + 565: freight car + 566: French horn + 567: frying pan + 568: fur coat + 569: garbage truck + 570: gas mask + 571: gas pump + 572: goblet + 573: go-kart + 574: golf ball + 575: golf cart + 576: gondola + 577: gong + 578: gown + 579: grand piano + 580: greenhouse + 581: grille + 582: grocery store + 583: guillotine + 584: barrette + 585: hair spray + 586: half-track + 587: hammer + 588: hamper + 589: hair dryer + 590: hand-held computer + 591: handkerchief + 592: hard disk drive + 593: harmonica + 594: harp + 595: harvester + 596: hatchet + 597: holster + 598: home theater + 599: honeycomb + 600: hook + 601: hoop skirt + 602: horizontal bar + 603: horse-drawn vehicle + 604: hourglass + 605: iPod + 606: clothes iron + 607: jack-o'-lantern + 608: jeans + 609: jeep + 610: T-shirt + 611: jigsaw puzzle + 612: pulled rickshaw + 613: joystick + 614: kimono + 615: knee pad + 616: knot + 617: lab coat + 618: ladle + 619: lampshade + 620: laptop computer + 621: lawn mower + 622: lens cap + 623: paper knife + 624: library + 625: lifeboat + 626: lighter + 627: limousine + 628: ocean liner + 629: lipstick + 630: slip-on shoe + 631: lotion + 632: speaker + 633: loupe + 634: sawmill + 635: magnetic compass + 636: mail bag + 637: mailbox + 638: tights + 639: tank suit + 640: manhole cover + 641: maraca + 642: marimba + 643: mask + 644: match + 645: maypole + 646: maze + 647: measuring cup + 648: medicine chest + 649: megalith + 650: microphone + 651: microwave oven + 652: military uniform + 653: milk can + 654: minibus + 655: miniskirt + 656: minivan + 657: missile + 658: mitten + 659: mixing bowl + 660: mobile home + 661: Model T + 662: modem + 663: monastery + 664: monitor + 665: moped + 666: mortar + 667: square academic cap + 668: mosque + 669: mosquito net + 670: scooter + 671: mountain bike + 672: tent + 673: computer mouse + 674: mousetrap + 675: moving van + 676: muzzle + 677: nail + 678: neck brace + 679: necklace + 680: nipple + 681: notebook computer + 682: obelisk + 683: oboe + 684: ocarina + 685: odometer + 686: oil filter + 687: organ + 688: oscilloscope + 689: overskirt + 690: bullock cart + 691: oxygen mask + 692: packet + 693: paddle + 694: paddle wheel + 695: padlock + 696: paintbrush + 697: pajamas + 698: palace + 699: pan flute + 700: paper towel + 701: parachute + 702: parallel bars + 703: park bench + 704: parking meter + 705: passenger car + 706: patio + 707: payphone + 708: pedestal + 709: pencil case + 710: pencil sharpener + 711: perfume + 712: Petri dish + 713: photocopier + 714: plectrum + 715: Pickelhaube + 716: picket fence + 717: pickup truck + 718: pier + 719: piggy bank + 720: pill bottle + 721: pillow + 722: ping-pong ball + 723: pinwheel + 724: pirate ship + 725: pitcher + 726: hand plane + 727: planetarium + 728: plastic bag + 729: plate rack + 730: plow + 731: plunger + 732: Polaroid camera + 733: pole + 734: police van + 735: poncho + 736: billiard table + 737: soda bottle + 738: pot + 739: potter's wheel + 740: power drill + 741: prayer rug + 742: printer + 743: prison + 744: projectile + 745: projector + 746: hockey puck + 747: punching bag + 748: purse + 749: quill + 750: quilt + 751: race car + 752: racket + 753: radiator + 754: radio + 755: radio telescope + 756: rain barrel + 757: recreational vehicle + 758: reel + 759: reflex camera + 760: refrigerator + 761: remote control + 762: restaurant + 763: revolver + 764: rifle + 765: rocking chair + 766: rotisserie + 767: eraser + 768: rugby ball + 769: ruler + 770: running shoe + 771: safe + 772: safety pin + 773: salt shaker + 774: sandal + 775: sarong + 776: saxophone + 777: scabbard + 778: weighing scale + 779: school bus + 780: schooner + 781: scoreboard + 782: CRT screen + 783: screw + 784: screwdriver + 785: seat belt + 786: sewing machine + 787: shield + 788: shoe store + 789: shoji + 790: shopping basket + 791: shopping cart + 792: shovel + 793: shower cap + 794: shower curtain + 795: ski + 796: ski mask + 797: sleeping bag + 798: slide rule + 799: sliding door + 800: slot machine + 801: snorkel + 802: snowmobile + 803: snowplow + 804: soap dispenser + 805: soccer ball + 806: sock + 807: solar thermal collector + 808: sombrero + 809: soup bowl + 810: space bar + 811: space heater + 812: space shuttle + 813: spatula + 814: motorboat + 815: spider web + 816: spindle + 817: sports car + 818: spotlight + 819: stage + 820: steam locomotive + 821: through arch bridge + 822: steel drum + 823: stethoscope + 824: scarf + 825: stone wall + 826: stopwatch + 827: stove + 828: strainer + 829: tram + 830: stretcher + 831: couch + 832: stupa + 833: submarine + 834: suit + 835: sundial + 836: sunglass + 837: sunglasses + 838: sunscreen + 839: suspension bridge + 840: mop + 841: sweatshirt + 842: swimsuit + 843: swing + 844: switch + 845: syringe + 846: table lamp + 847: tank + 848: tape player + 849: teapot + 850: teddy bear + 851: television + 852: tennis ball + 853: thatched roof + 854: front curtain + 855: thimble + 856: threshing machine + 857: throne + 858: tile roof + 859: toaster + 860: tobacco shop + 861: toilet seat + 862: torch + 863: totem pole + 864: tow truck + 865: toy store + 866: tractor + 867: semi-trailer truck + 868: tray + 869: trench coat + 870: tricycle + 871: trimaran + 872: tripod + 873: triumphal arch + 874: trolleybus + 875: trombone + 876: tub + 877: turnstile + 878: typewriter keyboard + 879: umbrella + 880: unicycle + 881: upright piano + 882: vacuum cleaner + 883: vase + 884: vault + 885: velvet + 886: vending machine + 887: vestment + 888: viaduct + 889: violin + 890: volleyball + 891: waffle iron + 892: wall clock + 893: wallet + 894: wardrobe + 895: military aircraft + 896: sink + 897: washing machine + 898: water bottle + 899: water jug + 900: water tower + 901: whiskey jug + 902: whistle + 903: wig + 904: window screen + 905: window shade + 906: Windsor tie + 907: wine bottle + 908: wing + 909: wok + 910: wooden spoon + 911: wool + 912: split-rail fence + 913: shipwreck + 914: yawl + 915: yurt + 916: website + 917: comic book + 918: crossword + 919: traffic sign + 920: traffic light + 921: dust jacket + 922: menu + 923: plate + 924: guacamole + 925: consomme + 926: hot pot + 927: trifle + 928: ice cream + 929: ice pop + 930: baguette + 931: bagel + 932: pretzel + 933: cheeseburger + 934: hot dog + 935: mashed potato + 936: cabbage + 937: broccoli + 938: cauliflower + 939: zucchini + 940: spaghetti squash + 941: acorn squash + 942: butternut squash + 943: cucumber + 944: artichoke + 945: bell pepper + 946: cardoon + 947: mushroom + 948: Granny Smith + 949: strawberry + 950: orange + 951: lemon + 952: fig + 953: pineapple + 954: banana + 955: jackfruit + 956: custard apple + 957: pomegranate + 958: hay + 959: carbonara + 960: chocolate syrup + 961: dough + 962: meatloaf + 963: pizza + 964: pot pie + 965: burrito + 966: red wine + 967: espresso + 968: cup + 969: eggnog + 970: alp + 971: bubble + 972: cliff + 973: coral reef + 974: geyser + 975: lakeshore + 976: promontory + 977: shoal + 978: seashore + 979: valley + 980: volcano + 981: baseball player + 982: bridegroom + 983: scuba diver + 984: rapeseed + 985: daisy + 986: yellow lady's slipper + 987: corn + 988: acorn + 989: rose hip + 990: horse chestnut seed + 991: coral fungus + 992: agaric + 993: gyromitra + 994: stinkhorn mushroom + 995: earth star + 996: hen-of-the-woods + 997: bolete + 998: ear + 999: toilet paper + + +# Download script/URL (optional) +download: data/scripts/get_imagenet.sh diff --git a/ultralytics/yolo/data/datasets/Objects365.yaml b/ultralytics/yolo/data/datasets/Objects365.yaml new file mode 100644 index 0000000..8a4e071 --- /dev/null +++ b/ultralytics/yolo/data/datasets/Objects365.yaml @@ -0,0 +1,438 @@ +# Ultralytics YOLO 🚀, GPL-3.0 license +# Objects365 dataset https://www.objects365.org/ by Megvii +# Example usage: python train.py --data Objects365.yaml +# parent +# ├── yolov5 +# └── 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 utils.general import Path, check_requirements, download, np, xyxy2xywhn + + 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, delete=False) # annotations json + download([f'{url}patch{i}.tar.gz' for i in range(patches)], dir=images, curl=True, delete=False, threads=8) + elif split == 'val': + download([f'{url}zhiyuan_objv2_{split}.json'], dir=dir, delete=False) # annotations json + download([f'{url}images/v1/patch{i}.tar.gz' for i in range(15 + 1)], dir=images, curl=True, delete=False, threads=8) + download([f'{url}images/v2/patch{i}.tar.gz' for i in range(16, patches)], dir=images, curl=True, delete=False, 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) diff --git a/ultralytics/yolo/data/datasets/SKU-110K.yaml b/ultralytics/yolo/data/datasets/SKU-110K.yaml new file mode 100644 index 0000000..9bfad4f --- /dev/null +++ b/ultralytics/yolo/data/datasets/SKU-110K.yaml @@ -0,0 +1,53 @@ +# Ultralytics YOLO 🚀, GPL-3.0 license +# SKU-110K retail items dataset https://github.com/eg4000/SKU110K_CVPR19 by Trax Retail +# Example usage: python train.py --data SKU-110K.yaml +# parent +# ├── yolov5 +# └── 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 tqdm import tqdm + from utils.general import np, pd, Path, download, 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, delete=False) + + # 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 diff --git a/ultralytics/yolo/data/datasets/VOC.yaml b/ultralytics/yolo/data/datasets/VOC.yaml new file mode 100644 index 0000000..96d232e --- /dev/null +++ b/ultralytics/yolo/data/datasets/VOC.yaml @@ -0,0 +1,100 @@ +# Ultralytics YOLO 🚀, GPL-3.0 license +# PASCAL VOC dataset http://host.robots.ox.ac.uk/pascal/VOC by University of Oxford +# Example usage: python train.py --data VOC.yaml +# parent +# ├── yolov5 +# └── 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 utils.general import download, 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', delete=False, curl=True, threads=3) + + # 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 diff --git a/ultralytics/yolo/data/datasets/VisDrone.yaml b/ultralytics/yolo/data/datasets/VisDrone.yaml new file mode 100644 index 0000000..6173061 --- /dev/null +++ b/ultralytics/yolo/data/datasets/VisDrone.yaml @@ -0,0 +1,70 @@ +# Ultralytics YOLO 🚀, GPL-3.0 license +# VisDrone2019-DET dataset https://github.com/VisDrone/VisDrone-Dataset by Tianjin University +# Example usage: python train.py --data VisDrone.yaml +# parent +# ├── yolov5 +# └── 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: | + from utils.general import download, os, Path + + 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(os.sep + 'annotations' + os.sep, 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 diff --git a/ultralytics/yolo/data/datasets/xView.yaml b/ultralytics/yolo/data/datasets/xView.yaml new file mode 100644 index 0000000..f11f13e --- /dev/null +++ b/ultralytics/yolo/data/datasets/xView.yaml @@ -0,0 +1,153 @@ +# Ultralytics YOLO 🚀, GPL-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! -------- +# Example usage: python train.py --data xView.yaml +# parent +# ├── yolov5 +# └── 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 utils.dataloaders import autosplit + from utils.general import download, 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, delete=False) + + # 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') diff --git a/ultralytics/yolo/data/utils.py b/ultralytics/yolo/data/utils.py index 311fdf8..744fa0d 100644 --- a/ultralytics/yolo/data/utils.py +++ b/ultralytics/yolo/data/utils.py @@ -288,5 +288,6 @@ def check_dataset(dataset: str): train_set = data_dir / "train" test_set = data_dir / 'test' if (data_dir / 'test').exists() else data_dir / 'val' # data/test or data/val nc = len([x for x in (data_dir / 'train').glob('*') if x.is_dir()]) # number of classes - names = [name for name in os.listdir(data_dir / 'train') if os.path.isdir(data_dir / 'train' / name)] + names = [x.name for x in (data_dir / 'train').iterdir() if x.is_dir()] # class names list + names = dict(enumerate(sorted(names))) return {"train": train_set, "val": test_set, "nc": nc, "names": names} diff --git a/ultralytics/yolo/engine/exporter.py b/ultralytics/yolo/engine/exporter.py index 76f3b3e..8b58ce1 100644 --- a/ultralytics/yolo/engine/exporter.py +++ b/ultralytics/yolo/engine/exporter.py @@ -256,7 +256,7 @@ class Exporter: @try_export def _export_torchscript(self, prefix=colorstr('TorchScript:')): - # YOLOv5 TorchScript model export + # YOLOv8 TorchScript model export LOGGER.info(f'\n{prefix} starting export with torch {torch.__version__}...') f = self.file.with_suffix('.torchscript') @@ -273,7 +273,7 @@ class Exporter: @try_export def _export_onnx(self, prefix=colorstr('ONNX:')): - # YOLOv5 ONNX export + # YOLOv8 ONNX export check_requirements('onnx>=1.12.0') import onnx # noqa @@ -326,7 +326,7 @@ class Exporter: @try_export def _export_openvino(self, prefix=colorstr('OpenVINO:')): - # YOLOv5 OpenVINO export + # YOLOv8 OpenVINO export check_requirements('openvino-dev') # requires openvino-dev: https://pypi.org/project/openvino-dev/ import openvino.inference_engine as ie # noqa @@ -341,7 +341,7 @@ class Exporter: @try_export def _export_paddle(self, prefix=colorstr('PaddlePaddle:')): - # YOLOv5 Paddle export + # YOLOv8 Paddle export check_requirements(('paddlepaddle', 'x2paddle')) import x2paddle # noqa from x2paddle.convert import pytorch2paddle # noqa @@ -355,7 +355,7 @@ class Exporter: @try_export def _export_coreml(self, prefix=colorstr('CoreML:')): - # YOLOv5 CoreML export + # YOLOv8 CoreML export check_requirements('coremltools>=6.0') import coremltools as ct # noqa @@ -395,7 +395,7 @@ class Exporter: @try_export def _export_engine(self, workspace=4, verbose=False, prefix=colorstr('TensorRT:')): - # YOLOv5 TensorRT export https://developer.nvidia.com/tensorrt + # YOLOv8 TensorRT export https://developer.nvidia.com/tensorrt assert self.im.device.type != 'cpu', 'export running on CPU but must be on GPU, i.e. `device==0`' try: import tensorrt as trt # noqa @@ -460,7 +460,7 @@ class Exporter: conf_thres=0.25, prefix=colorstr('TensorFlow SavedModel:')): - # YOLOv5 TensorFlow SavedModel export + # YOLOv8 TensorFlow SavedModel export try: import tensorflow as tf # noqa except ImportError: @@ -493,7 +493,7 @@ class Exporter: iou_thres=0.45, conf_thres=0.25, prefix=colorstr('TensorFlow SavedModel:')): - # YOLOv5 TensorFlow SavedModel export + # YOLOv8 TensorFlow SavedModel export try: import tensorflow as tf # noqa except ImportError: @@ -533,7 +533,7 @@ class Exporter: @try_export def _export_pb(self, keras_model, file, prefix=colorstr('TensorFlow GraphDef:')): - # YOLOv5 TensorFlow GraphDef *.pb export https://github.com/leimao/Frozen_Graph_TensorFlow + # YOLOv8 TensorFlow GraphDef *.pb export https://github.com/leimao/Frozen_Graph_TensorFlow import tensorflow as tf # noqa from tensorflow.python.framework.convert_to_constants import convert_variables_to_constants_v2 # noqa @@ -549,7 +549,7 @@ class Exporter: @try_export def _export_tflite(self, keras_model, int8, data, nms, agnostic_nms, prefix=colorstr('TensorFlow Lite:')): - # YOLOv5 TensorFlow Lite export + # YOLOv8 TensorFlow Lite export import tensorflow as tf # noqa LOGGER.info(f'\n{prefix} starting export with tensorflow {tf.__version__}...') @@ -589,7 +589,7 @@ class Exporter: @try_export def _export_edgetpu(self, prefix=colorstr('Edge TPU:')): - # YOLOv5 Edge TPU export https://coral.ai/docs/edgetpu/models-intro/ + # YOLOv8 Edge TPU export https://coral.ai/docs/edgetpu/models-intro/ cmd = 'edgetpu_compiler --version' help_url = 'https://coral.ai/docs/edgetpu/compiler/' assert platform.system() == 'Linux', f'export only supported on Linux. See {help_url}' @@ -615,7 +615,7 @@ class Exporter: @try_export def _export_tfjs(self, prefix=colorstr('TensorFlow.js:')): - # YOLOv5 TensorFlow.js export + # YOLOv8 TensorFlow.js export check_requirements('tensorflowjs') import tensorflowjs as tfjs # noqa @@ -673,7 +673,7 @@ class Exporter: tmp_file.unlink() def _pipeline_coreml(self, model, prefix=colorstr('CoreML Pipeline:')): - # YOLOv5 CoreML pipeline + # YOLOv8 CoreML pipeline import coremltools as ct # noqa LOGGER.info(f'{prefix} starting pipeline with coremltools {ct.__version__}...') diff --git a/ultralytics/yolo/engine/predictor.py b/ultralytics/yolo/engine/predictor.py index c3e93cf..309e7d1 100644 --- a/ultralytics/yolo/engine/predictor.py +++ b/ultralytics/yolo/engine/predictor.py @@ -127,13 +127,26 @@ class BasePredictor: if self.args.show: self.args.show = check_imshow(warn=True) if webcam: - self.args.show = check_imshow(warn=True) - self.dataset = LoadStreams(source, imgsz=imgsz, stride=stride, auto=pt, vid_stride=self.args.vid_stride) + self.dataset = LoadStreams(source, + imgsz=imgsz, + stride=stride, + auto=pt, + transforms=getattr(model.model, 'transforms', None), + vid_stride=self.args.vid_stride) bs = len(self.dataset) elif screenshot: - self.dataset = LoadScreenshots(source, imgsz=imgsz, stride=stride, auto=pt) + self.dataset = LoadScreenshots(source, + imgsz=imgsz, + stride=stride, + auto=pt, + transforms=getattr(model.model, 'transforms', None)) else: - self.dataset = LoadImages(source, imgsz=imgsz, stride=stride, auto=pt, vid_stride=self.args.vid_stride) + self.dataset = LoadImages(source, + imgsz=imgsz, + stride=stride, + auto=pt, + transforms=getattr(model.model, 'transforms', None), + vid_stride=self.args.vid_stride) self.vid_path, self.vid_writer = [None] * bs, [None] * bs model.warmup(imgsz=(1 if pt or model.triton else bs, 3, *imgsz)) # warmup diff --git a/ultralytics/yolo/v8/classify/predict.py b/ultralytics/yolo/v8/classify/predict.py index 3ef879b..22a5706 100644 --- a/ultralytics/yolo/v8/classify/predict.py +++ b/ultralytics/yolo/v8/classify/predict.py @@ -38,7 +38,7 @@ class ClassificationPredictor(BasePredictor): log_string += '%gx%g ' % im.shape[2:] # print string self.annotator = self.get_annotator(im0) - prob = preds[idx] + prob = preds[idx].softmax(0) self.all_outputs.append(prob) # Print results top5i = prob.argsort(0, descending=True)[:5].tolist() # top 5 indices diff --git a/ultralytics/yolo/v8/classify/train.py b/ultralytics/yolo/v8/classify/train.py index 46660e1..10ae535 100644 --- a/ultralytics/yolo/v8/classify/train.py +++ b/ultralytics/yolo/v8/classify/train.py @@ -25,6 +25,8 @@ class ClassificationTrainer(BaseTrainer): def get_model(self, cfg=None, weights=None, verbose=True): model = ClassificationModel(cfg, nc=self.data["nc"]) + if weights: + model.load(weights) pretrained = False for m in model.modules(): @@ -35,9 +37,6 @@ class ClassificationTrainer(BaseTrainer): for p in model.parameters(): p.requires_grad = True # for training - if weights: - model.load(weights) - # Update defaults if self.args.imgsz == 640: self.args.imgsz = 224 @@ -68,12 +67,15 @@ class ClassificationTrainer(BaseTrainer): return # dont return ckpt. Classification doesn't support resume def get_dataloader(self, dataset_path, batch_size=16, rank=0, mode="train"): - return build_classification_dataloader(path=dataset_path, - imgsz=self.args.imgsz, - batch_size=batch_size if mode == "train" else (batch_size * 2), - augment=mode == "train", - rank=rank, - workers=self.args.workers) + loader = build_classification_dataloader(path=dataset_path, + imgsz=self.args.imgsz, + batch_size=batch_size if mode == "train" else (batch_size * 2), + augment=mode == "train", + rank=rank, + workers=self.args.workers) + if mode != "train": + self.model.transforms = loader.dataset.torch_transforms # attach inference transforms + return loader def preprocess_batch(self, batch): batch["img"] = batch["img"].to(self.device) @@ -141,19 +143,18 @@ def train(cfg): cfg.weight_decay = 5e-5 cfg.label_smoothing = 0.1 cfg.warmup_epochs = 0.0 - trainer = ClassificationTrainer(cfg) - trainer.train() - # from ultralytics import YOLO - # model = YOLO(cfg.model) - # model.train(**cfg) + # trainer = ClassificationTrainer(cfg) + # trainer.train() + from ultralytics import YOLO + model = YOLO(cfg.model) + model.train(**cfg) if __name__ == "__main__": """ - CLI usage: - python ultralytics/yolo/v8/classify/train.py model=resnet18 data=imagenette160 epochs=1 imgsz=224 - - TODO: - Direct cli support, i.e, yolov8 classify_train args.epochs 10 + yolo task=classify mode=train model=yolov8n-cls.pt data=mnist160 epochs=10 imgsz=32 + yolo task=classify mode=val model=runs/classify/train/weights/last.pt data=mnist160 imgsz=32 + yolo task=classify mode=predict model=runs/classify/train/weights/last.pt imgsz=32 source=ultralytics/assets/bus.jpg + yolo mode=export model=runs/classify/train/weights/last.pt imgsz=32 format=torchscript """ train()