Ultralytics master

README.md

@@ -72,7 +72,7 @@ $ pip install -r requirements.txt
 * [Supervisely Ecosystem](https://github.com/ultralytics/yolov5/issues/2518)  🌟 NEW
 * [Multi-GPU Training](https://github.com/ultralytics/yolov5/issues/475)
 * [PyTorch Hub](https://github.com/ultralytics/yolov5/issues/36)  ⭐ NEW
-* [ONNX and TorchScript Export](https://github.com/ultralytics/yolov5/issues/251)
+* [TorchScript, ONNX, CoreML Export](https://github.com/ultralytics/yolov5/issues/251) 🚀
 * [Test-Time Augmentation (TTA)](https://github.com/ultralytics/yolov5/issues/303)
 * [Model Ensembling](https://github.com/ultralytics/yolov5/issues/318)
 * [Model Pruning/Sparsity](https://github.com/ultralytics/yolov5/issues/304)
@@ -130,7 +130,7 @@ import torch
 model = torch.hub.load('ultralytics/yolov5', 'yolov5s')
 
 # Image
-img = 'https://github.com/ultralytics/yolov5/raw/master/data/images/zidane.jpg'
+img = 'https://ultralytics.com/images/zidane.jpg'
 
 # Inference
 results = model(img)

data/GlobalWheat2020.yaml

@@ -0,0 +1,55 @@
+# Global Wheat 2020 dataset http://www.global-wheat.com/
+# Train command: python train.py --data GlobalWheat2020.yaml
+# Default dataset location is next to YOLOv5:
+#   /parent_folder
+#     /datasets/GlobalWheat2020
+#     /yolov5
+
+
+# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
+train: # 3422 images
+  - ../datasets/GlobalWheat2020/images/arvalis_1
+  - ../datasets/GlobalWheat2020/images/arvalis_2
+  - ../datasets/GlobalWheat2020/images/arvalis_3
+  - ../datasets/GlobalWheat2020/images/ethz_1
+  - ../datasets/GlobalWheat2020/images/rres_1
+  - ../datasets/GlobalWheat2020/images/inrae_1
+  - ../datasets/GlobalWheat2020/images/usask_1
+
+val: # 748 images (WARNING: train set contains ethz_1)
+  - ../datasets/GlobalWheat2020/images/ethz_1
+
+test: # 1276 images
+  - ../datasets/GlobalWheat2020/images/utokyo_1
+  - ../datasets/GlobalWheat2020/images/utokyo_2
+  - ../datasets/GlobalWheat2020/images/nau_1
+  - ../datasets/GlobalWheat2020/images/uq_1
+
+# number of classes
+nc: 1
+
+# class names
+names: [ 'wheat_head' ]
+
+
+# download command/URL (optional) --------------------------------------------------------------------------------------
+download: |
+  from utils.general import download, Path
+
+  # Download
+  dir = Path('../datasets/GlobalWheat2020')  # dataset directory
+  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

data/SKU-110K.yaml

@@ -0,0 +1,52 @@
+# SKU-110K retail items dataset https://github.com/eg4000/SKU110K_CVPR19
+# Train command: python train.py --data SKU-110K.yaml
+# Default dataset location is next to YOLOv5:
+#   /parent_folder
+#     /datasets/SKU-110K
+#     /yolov5
+
+
+# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
+train: ../datasets/SKU-110K/train.txt  # 8219 images
+val: ../datasets/SKU-110K/val.txt  # 588 images
+test: ../datasets/SKU-110K/test.txt  # 2936 images
+
+# number of classes
+nc: 1
+
+# class names
+names: [ 'object' ]
+
+
+# download command/URL (optional) --------------------------------------------------------------------------------------
+download: |
+  import shutil
+  from tqdm import tqdm
+  from utils.general import np, pd, Path, download, xyxy2xywh
+
+  # Download
+  datasets = Path('../datasets')  # download directory
+  urls = ['http://trax-geometry.s3.amazonaws.com/cvpr_challenge/SKU110K_fixed.tar.gz']
+  download(urls, dir=datasets, delete=False)
+
+  # Rename directories
+  dir = (datasets / 'SKU-110K')
+  if dir.exists():
+      shutil.rmtree(dir)
+  (datasets / '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

data/visdrone.yaml → data/VisDrone.yaml

@@ -1,5 +1,5 @@
 # VisDrone2019-DET dataset https://github.com/VisDrone/VisDrone-Dataset
-# Train command: python train.py --data visdrone.yaml
+# Train command: python train.py --data VisDrone.yaml
 # Default dataset location is next to YOLOv5:
 #   /parent_folder
 #     /VisDrone
@@ -20,11 +20,7 @@ names: [ 'pedestrian', 'people', 'bicycle', 'car', 'van', 'truck', 'tricycle', '
 
 # download command/URL (optional) --------------------------------------------------------------------------------------
 download: |
-  import os
-  from pathlib import Path
-
-  from utils.general import download
-
+  from utils.general import download, os, Path
 
   def visdrone2yolo(dir):
       from PIL import Image

data/hyp.finetune_objects365.yaml

@@ -0,0 +1,28 @@
+lr0: 0.00258
+lrf: 0.17
+momentum: 0.779
+weight_decay: 0.00058
+warmup_epochs: 1.33
+warmup_momentum: 0.86
+warmup_bias_lr: 0.0711
+box: 0.0539
+cls: 0.299
+cls_pw: 0.825
+obj: 0.632
+obj_pw: 1.0
+iou_t: 0.2
+anchor_t: 3.44
+anchors: 3.2
+fl_gamma: 0.0
+hsv_h: 0.0188
+hsv_s: 0.704
+hsv_v: 0.36
+degrees: 0.0
+translate: 0.0902
+scale: 0.491
+shear: 0.0
+perspective: 0.0
+flipud: 0.0
+fliplr: 0.5
+mosaic: 1.0
+mixup: 0.0

data/objects365.yaml

@@ -0,0 +1,102 @@
+# Objects365 dataset https://www.objects365.org/
+# Train command: python train.py --data objects365.yaml
+# Default dataset location is next to YOLOv5:
+#   /parent_folder
+#     /datasets/objects365
+#     /yolov5
+
+# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
+train: ../datasets/objects365/images/train  # 1742289 images
+val: ../datasets/objects365/images/val # 5570 images
+
+# number of classes
+nc: 365
+
+# class names
+names: [ 'Person', 'Sneakers', 'Chair', 'Other Shoes', 'Hat', 'Car', 'Lamp', 'Glasses', 'Bottle', 'Desk', 'Cup',
+         'Street Lights', 'Cabinet/shelf', 'Handbag/Satchel', 'Bracelet', 'Plate', 'Picture/Frame', 'Helmet', 'Book',
+         'Gloves', 'Storage box', 'Boat', 'Leather Shoes', 'Flower', 'Bench', 'Potted Plant', 'Bowl/Basin', 'Flag',
+         'Pillow', 'Boots', 'Vase', 'Microphone', 'Necklace', 'Ring', 'SUV', 'Wine Glass', 'Belt', 'Monitor/TV',
+         'Backpack', 'Umbrella', 'Traffic Light', 'Speaker', 'Watch', 'Tie', 'Trash bin Can', 'Slippers', 'Bicycle',
+         'Stool', 'Barrel/bucket', 'Van', 'Couch', 'Sandals', 'Basket', 'Drum', 'Pen/Pencil', 'Bus', 'Wild Bird',
+         'High Heels', 'Motorcycle', 'Guitar', 'Carpet', 'Cell Phone', 'Bread', 'Camera', 'Canned', 'Truck',
+         'Traffic cone', 'Cymbal', 'Lifesaver', 'Towel', 'Stuffed Toy', 'Candle', 'Sailboat', 'Laptop', 'Awning',
+         'Bed', 'Faucet', 'Tent', 'Horse', 'Mirror', 'Power outlet', 'Sink', 'Apple', 'Air Conditioner', 'Knife',
+         'Hockey Stick', 'Paddle', 'Pickup Truck', 'Fork', 'Traffic Sign', 'Balloon', 'Tripod', 'Dog', 'Spoon', 'Clock',
+         'Pot', 'Cow', 'Cake', 'Dinning Table', 'Sheep', 'Hanger', 'Blackboard/Whiteboard', 'Napkin', 'Other Fish',
+         'Orange/Tangerine', 'Toiletry', 'Keyboard', 'Tomato', 'Lantern', 'Machinery Vehicle', 'Fan',
+         'Green Vegetables', 'Banana', 'Baseball Glove', 'Airplane', 'Mouse', 'Train', 'Pumpkin', 'Soccer', 'Skiboard',
+         'Luggage', 'Nightstand', 'Tea pot', 'Telephone', 'Trolley', 'Head Phone', 'Sports Car', 'Stop Sign',
+         'Dessert', 'Scooter', 'Stroller', 'Crane', 'Remote', 'Refrigerator', 'Oven', 'Lemon', 'Duck', 'Baseball Bat',
+         'Surveillance Camera', 'Cat', 'Jug', 'Broccoli', 'Piano', 'Pizza', 'Elephant', 'Skateboard', 'Surfboard',
+         'Gun', 'Skating and Skiing shoes', 'Gas stove', 'Donut', 'Bow Tie', 'Carrot', 'Toilet', 'Kite', 'Strawberry',
+         'Other Balls', 'Shovel', 'Pepper', 'Computer Box', 'Toilet Paper', 'Cleaning Products', 'Chopsticks',
+         'Microwave', 'Pigeon', 'Baseball', 'Cutting/chopping Board', 'Coffee Table', 'Side Table', 'Scissors',
+         'Marker', 'Pie', 'Ladder', 'Snowboard', 'Cookies', 'Radiator', 'Fire Hydrant', 'Basketball', 'Zebra', 'Grape',
+         'Giraffe', 'Potato', 'Sausage', 'Tricycle', 'Violin', 'Egg', 'Fire Extinguisher', 'Candy', 'Fire Truck',
+         'Billiards', 'Converter', 'Bathtub', 'Wheelchair', 'Golf Club', 'Briefcase', 'Cucumber', 'Cigar/Cigarette',
+         'Paint Brush', 'Pear', 'Heavy Truck', 'Hamburger', 'Extractor', 'Extension Cord', 'Tong', 'Tennis Racket',
+         'Folder', 'American Football', 'earphone', 'Mask', 'Kettle', 'Tennis', 'Ship', 'Swing', 'Coffee Machine',
+         'Slide', 'Carriage', 'Onion', 'Green beans', 'Projector', 'Frisbee', 'Washing Machine/Drying Machine',
+         'Chicken', 'Printer', 'Watermelon', 'Saxophone', 'Tissue', 'Toothbrush', 'Ice cream', 'Hot-air balloon',
+         'Cello', 'French Fries', 'Scale', 'Trophy', 'Cabbage', 'Hot dog', 'Blender', 'Peach', 'Rice', 'Wallet/Purse',
+         'Volleyball', 'Deer', 'Goose', 'Tape', 'Tablet', 'Cosmetics', 'Trumpet', 'Pineapple', 'Golf Ball',
+         'Ambulance', 'Parking meter', 'Mango', 'Key', 'Hurdle', 'Fishing Rod', 'Medal', 'Flute', 'Brush', 'Penguin',
+         'Megaphone', 'Corn', 'Lettuce', 'Garlic', 'Swan', 'Helicopter', 'Green Onion', 'Sandwich', 'Nuts',
+         'Speed Limit Sign', 'Induction Cooker', 'Broom', 'Trombone', 'Plum', 'Rickshaw', 'Goldfish', 'Kiwi fruit',
+         'Router/modem', 'Poker Card', 'Toaster', 'Shrimp', 'Sushi', 'Cheese', 'Notepaper', 'Cherry', 'Pliers', 'CD',
+         'Pasta', 'Hammer', 'Cue', 'Avocado', 'Hamimelon', 'Flask', 'Mushroom', 'Screwdriver', 'Soap', 'Recorder',
+         'Bear', 'Eggplant', 'Board Eraser', 'Coconut', 'Tape Measure/Ruler', 'Pig', 'Showerhead', 'Globe', 'Chips',
+         'Steak', 'Crosswalk Sign', 'Stapler', 'Camel', 'Formula 1', 'Pomegranate', 'Dishwasher', 'Crab',
+         'Hoverboard', 'Meat ball', 'Rice Cooker', 'Tuba', 'Calculator', 'Papaya', 'Antelope', 'Parrot', 'Seal',
+         'Butterfly', 'Dumbbell', 'Donkey', 'Lion', 'Urinal', 'Dolphin', 'Electric Drill', 'Hair Dryer', 'Egg tart',
+         'Jellyfish', 'Treadmill', 'Lighter', 'Grapefruit', 'Game board', 'Mop', 'Radish', 'Baozi', 'Target', 'French',
+         'Spring Rolls', 'Monkey', 'Rabbit', 'Pencil Case', 'Yak', 'Red Cabbage', 'Binoculars', 'Asparagus', 'Barbell',
+         'Scallop', 'Noddles', 'Comb', 'Dumpling', 'Oyster', 'Table Tennis paddle', 'Cosmetics Brush/Eyeliner Pencil',
+         'Chainsaw', 'Eraser', 'Lobster', 'Durian', 'Okra', 'Lipstick', 'Cosmetics Mirror', 'Curling', 'Table Tennis' ]
+
+
+# download command/URL (optional) --------------------------------------------------------------------------------------
+download: |
+  from pycocotools.coco import COCO
+  from tqdm import tqdm
+
+  from utils.general import download, Path
+
+  # Make Directories
+  dir = Path('../datasets/objects365')  # dataset directory
+  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)
+
+  # Download
+  url = "https://dorc.ks3-cn-beijing.ksyun.com/data-set/2020Objects365%E6%95%B0%E6%8D%AE%E9%9B%86/train/"
+  download([url + 'zhiyuan_objv2_train.tar.gz'], dir=dir, delete=False)  # annotations json
+  download([url + f for f in [f'patch{i}.tar.gz' for i in range(51)]], dir=dir / 'images' / 'train',
+           curl=True, delete=False, threads=8)
+
+  # Move
+  train = dir / 'images' / 'train'
+  for f in tqdm(train.rglob('*.jpg'), desc=f'Moving images'):
+      f.rename(train / f.name)  # move to /images/train
+
+  # Labels
+  coco = COCO(dir / 'zhiyuan_objv2_train.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(dir / 'labels' / 'train' / 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)
+                      x, y = x + w / 2, y + h / 2  # xy to center
+                      file.write(f"{cid} {x / width:.5f} {y / height:.5f} {w / width:.5f} {h / height:.5f}\n")
+
+          except Exception as e:
+              print(e)

data/scripts/get_argoverse_hd.sh

@@ -36,7 +36,7 @@ for val in annotation_files:
         img_name = a['images'][img_id]['name']
         img_label_name = img_name[:-3] + "txt"
 
-        obj_class = annot['category_id']
+        cls = annot['category_id']  # instance class id
         x_center, y_center, width, height = annot['bbox']
         x_center = (x_center + width / 2) / 1920.  # offset and scale
         y_center = (y_center + height / 2) / 1200.  # offset and scale
@@ -46,11 +46,10 @@ for val in annotation_files:
         img_dir = "./labels/" + a['seq_dirs'][a['images'][annot['image_id']]['sid']]
 
         Path(img_dir).mkdir(parents=True, exist_ok=True)
-
         if img_dir + "/" + img_label_name not in label_dict:
             label_dict[img_dir + "/" + img_label_name] = []
 
-        label_dict[img_dir + "/" + img_label_name].append(f"{obj_class} {x_center} {y_center} {width} {height}\n")
+        label_dict[img_dir + "/" + img_label_name].append(f"{cls} {x_center} {y_center} {width} {height}\n")
 
     for filename in label_dict:
         with open(filename, "w") as file:

data/scripts/get_coco128.sh

@@ -0,0 +1,17 @@
+#!/bin/bash
+# COCO128 dataset https://www.kaggle.com/ultralytics/coco128
+# Download command: bash data/scripts/get_coco128.sh
+# Train command: python train.py --data coco128.yaml
+# Default dataset location is next to /yolov5:
+#   /parent_folder
+#     /coco128
+#     /yolov5
+
+# Download/unzip images and labels
+d='../' # unzip directory
+url=https://github.com/ultralytics/yolov5/releases/download/v1.0/
+f='coco128.zip' # or 'coco2017labels-segments.zip', 68 MB
+echo 'Downloading' $url$f ' ...'
+curl -L $url$f -o $f && unzip -q $f -d $d && rm $f & # download, unzip, remove in background
+
+wait # finish background tasks

detect.py

@@ -5,7 +5,6 @@
 import cv2
 import torch
 import torch.backends.cudnn as cudnn
-from numpy import random
 
 from models.experimental import attempt_load
 from utils.datasets import LoadStreams, LoadImages
@@ -69,7 +68,8 @@ def detect(opt):
         pred = model(img, augment=opt.augment)[0]
 
         # Apply NMS
-        pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms)
+        pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, opt.classes, opt.agnostic_nms,
+                                   max_det=opt.max_det)
         t2 = time_synchronized()
 
         # Apply Classifier
@@ -79,7 +79,7 @@ def detect(opt):
         # Process detections
         for i, det in enumerate(pred):  # detections per image
             if webcam:  # batch_size >= 1
-                p, s, im0, frame = path[i], '%g: ' % i, im0s[i].copy(), dataset.count
+                p, s, im0, frame = path[i], f'{i}: ', im0s[i].copy(), dataset.count
             else:
                 p, s, im0, frame = path, '', im0s.copy(), getattr(dataset, 'frame', 0)
 
@@ -88,6 +88,7 @@ def detect(opt):
             txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}')  # img.txt
             s += '%gx%g ' % img.shape[2:]  # print string
             gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]  # normalization gain whwh
+            imc = im0.copy() if opt.save_crop else im0  # for opt.save_crop
             if len(det):
                 # Rescale boxes from img_size to im0 size
                 det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()
@@ -108,10 +109,9 @@ def detect(opt):
                     if save_img or opt.save_crop or view_img:  # Add bbox to image
                         c = int(cls)  # integer class
                         label = None if opt.hide_labels else (names[c] if opt.hide_conf else f'{names[c]} {conf:.2f}')
-
                         plot_one_box(xyxy, im0, label=label, color=colors(c, True), line_thickness=opt.line_thickness)
                         if opt.save_crop:
-                            save_one_box(xyxy, im0s, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)
+                            save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True)
 
             # Print time (inference + NMS)
             print(f'{s}Done. ({t2 - t1:.3f}s)')
@@ -154,6 +154,7 @@ def detect(opt):
     parser.add_argument('--img-size', type=int, default=640, help='inference size (pixels)')
     parser.add_argument('--conf-thres', type=float, default=0.25, help='object confidence threshold')
     parser.add_argument('--iou-thres', type=float, default=0.45, help='IOU threshold for NMS')
+    parser.add_argument('--max-det', type=int, default=1000, help='maximum number of detections per image')
     parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
     parser.add_argument('--view-img', action='store_true', help='display results')
     parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
@@ -172,7 +173,7 @@ def detect(opt):
     parser.add_argument('--hide-conf', default=False, action='store_true', help='hide confidences')
     opt = parser.parse_args()
     print(opt)
-    check_requirements(exclude=('pycocotools', 'thop'))
+    check_requirements(exclude=('tensorboard', 'pycocotools', 'thop'))
 
     with torch.no_grad():
         if opt.update:  # update all models (to fix SourceChangeWarning)