Merge branch 'master' into udpate/tqdm

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -41,8 +41,8 @@ body:
     attributes:
       label: Bug
       description: Provide console output with error messages and/or screenshots of the bug.
-      placeholder: >
-        TIP: Include as much information as possible (screenshots, logs, tracebacks etc.) to receive the most helpful response.
+      placeholder: |
+        💡 ProTip! Include as much information as possible (screenshots, logs, tracebacks etc.) to receive the most helpful response.
     validations:
       required: true
 
@@ -51,7 +51,7 @@ body:
       label: Environment
       description: Please specify the software and hardware you used to produce the bug.
       placeholder: |
-        - YOLO: YOLOv5 🚀 v6.0-37-g620b535 torch 1.9.0+cu111 CUDA:0 (Tesla V100-SXM2-16GB, 16160.5MB)
+        - YOLO: YOLOv5 🚀 v6.0-67-g60e42e1 torch 1.9.0+cu111 CUDA:0 (A100-SXM4-40GB, 40536MiB)
         - OS: Ubuntu 20.04
         - Python: 3.9.0
     validations:
@@ -64,7 +64,9 @@ body:
         When asking a question, people will be better able to provide help if you provide code that they can easily understand and use to **reproduce** the problem.
         This is referred to by community members as creating a [minimal reproducible example](https://stackoverflow.com/help/minimal-reproducible-example).
       placeholder: |
-        # code to reproduce your issue here
+        ```
+        # Code to reproduce your issue here
+        ```
     validations:
       required: false
 

.github/ISSUE_TEMPLATE/question.yml

@@ -22,8 +22,8 @@ body:
     attributes:
       label: Question
       description: What is your question?
-      placeholder: >
-        TIP: Include as much information as possible (screenshots, links, reference etc.) to receive the most helpful response.
+      placeholder: |
+        💡 ProTip! Include as much information as possible (screenshots, logs, tracebacks etc.) to receive the most helpful response.
     validations:
       required: true
 

.pre-commit-config.yaml

@@ -30,12 +30,11 @@ repos:
         args: [--py36-plus]
         name: Upgrade code
 
-  # TODO
-  #- repo: https://github.com/PyCQA/isort
-  #  rev: 5.9.3
-  #  hooks:
-  #    - id: isort
-  #      name: imports
+  - repo: https://github.com/PyCQA/isort
+    rev: 5.9.3
+    hooks:
+      - id: isort
+        name: Sort imports
 
   # TODO
   #- repo: https://github.com/pre-commit/mirrors-yapf

Dockerfile

@@ -1,7 +1,7 @@
 # YOLOv5 🚀 by Ultralytics, GPL-3.0 license
 
 # Start FROM Nvidia PyTorch image https://ngc.nvidia.com/catalog/containers/nvidia:pytorch
-FROM nvcr.io/nvidia/pytorch:21.05-py3
+FROM nvcr.io/nvidia/pytorch:21.10-py3
 
 # Install linux packages
 RUN apt update && apt install -y zip htop screen libgl1-mesa-glx
@@ -11,8 +11,8 @@ COPY requirements.txt .
 RUN python -m pip install --upgrade pip
 RUN pip uninstall -y nvidia-tensorboard nvidia-tensorboard-plugin-dlprof
 RUN pip install --no-cache -r requirements.txt coremltools onnx gsutil notebook wandb>=0.12.2
-RUN pip install --no-cache -U torch torchvision numpy
-# RUN pip install --no-cache torch==1.9.1+cu111 torchvision==0.10.1+cu111 -f https://download.pytorch.org/whl/torch_stable.html
+RUN pip install --no-cache -U torch torchvision numpy Pillow
+# RUN pip install --no-cache torch==1.10.0+cu113 torchvision==0.11.1+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html
 
 # Create working directory
 RUN mkdir -p /usr/src/app

README.md

@@ -109,11 +109,11 @@ the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases) and
 
 ```bash
 $ python detect.py --source 0  # webcam
-                            file.jpg  # image
-                            file.mp4  # video
+                            img.jpg  # image
+                            vid.mp4  # video
                             path/  # directory
                             path/*.jpg  # glob
-                            'https://youtu.be/NUsoVlDFqZg'  # YouTube
+                            'https://youtu.be/Zgi9g1ksQHc'  # YouTube
                             'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream
 ```
 

data/coco128.yaml

@@ -27,4 +27,4 @@ names: ['person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 't
 
 
 # Download script/URL (optional)
-download: https://github.com/ultralytics/yolov5/releases/download/v1.0/coco128.zip
+download: https://ultralytics.com/assets/coco128.zip

detect.py

@@ -3,7 +3,13 @@
 Run inference on images, videos, directories, streams, etc.
 
 Usage:
-    $ python path/to/detect.py --source path/to/img.jpg --weights yolov5s.pt --img 640
+    $ python path/to/detect.py --weights yolov5s.pt --source 0  # webcam
+                                                             img.jpg  # image
+                                                             vid.mp4  # video
+                                                             path/  # directory
+                                                             path/*.jpg  # glob
+                                                             'https://youtu.be/Zgi9g1ksQHc'  # YouTube
+                                                             'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream
 """
 
 import argparse
@@ -12,7 +18,6 @@
 from pathlib import Path
 
 import cv2
-import numpy as np
 import torch
 import torch.backends.cudnn as cudnn
 
@@ -22,12 +27,12 @@
     sys.path.append(str(ROOT))  # add ROOT to PATH
 ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative
 
-from models.experimental import attempt_load
-from utils.datasets import LoadImages, LoadStreams
-from utils.general import apply_classifier, check_img_size, check_imshow, check_requirements, check_suffix, colorstr, \
-    increment_path, non_max_suppression, print_args, save_one_box, scale_coords, strip_optimizer, xyxy2xywh, LOGGER
-from utils.plots import Annotator, colors
-from utils.torch_utils import load_classifier, select_device, time_sync
+from models.common import DetectMultiBackend
+from utils.datasets import IMG_FORMATS, VID_FORMATS, LoadImages, LoadStreams
+from utils.general import (LOGGER, check_file, check_img_size, check_imshow, check_requirements, colorstr,
+                           increment_path, non_max_suppression, print_args, scale_coords, strip_optimizer, xyxy2xywh)
+from utils.plots import Annotator, colors, save_one_box
+from utils.torch_utils import select_device, time_sync
 
 
 @torch.no_grad()
@@ -59,120 +64,55 @@ def run(weights=ROOT / 'yolov5s.pt',  # model.pt path(s)
         ):
     source = str(source)
     save_img = not nosave and not source.endswith('.txt')  # save inference images
-    webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith(
-        ('rtsp://', 'rtmp://', 'http://', 'https://'))
+    is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
+    is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
+    webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file)
+    if is_url and is_file:
+        source = check_file(source)  # download
 
     # Directories
     save_dir = increment_path(Path(project) / name, exist_ok=exist_ok)  # increment run
     (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir
 
-    # Initialize
+    # Load model
     device = select_device(device)
-    half &= device.type != 'cpu'  # half precision only supported on CUDA
+    model = DetectMultiBackend(weights, device=device, dnn=dnn)
+    stride, names, pt, jit, onnx = model.stride, model.names, model.pt, model.jit, model.onnx
+    imgsz = check_img_size(imgsz, s=stride)  # check image size
 
-    # Load model
-    w = str(weights[0] if isinstance(weights, list) else weights)
-    classify, suffix, suffixes = False, Path(w).suffix.lower(), ['.pt', '.onnx', '.tflite', '.pb', '']
-    check_suffix(w, suffixes)  # check weights have acceptable suffix
-    pt, onnx, tflite, pb, saved_model = (suffix == x for x in suffixes)  # backend booleans
-    stride, names = 64, [f'class{i}' for i in range(1000)]  # assign defaults
+    # Half
+    half &= pt and device.type != 'cpu'  # half precision only supported by PyTorch on CUDA
     if pt:
-        model = torch.jit.load(w) if 'torchscript' in w else attempt_load(weights, map_location=device)
-        stride = int(model.stride.max())  # model stride
-        names = model.module.names if hasattr(model, 'module') else model.names  # get class names
-        if half:
-            model.half()  # to FP16
-        if classify:  # second-stage classifier
-            modelc = load_classifier(name='resnet50', n=2)  # initialize
-            modelc.load_state_dict(torch.load('resnet50.pt', map_location=device)['model']).to(device).eval()
-    elif onnx:
-        if dnn:
-            check_requirements(('opencv-python>=4.5.4',))
-            net = cv2.dnn.readNetFromONNX(w)
-        else:
-            check_requirements(('onnx', 'onnxruntime-gpu' if torch.has_cuda else 'onnxruntime'))
-            import onnxruntime
-            session = onnxruntime.InferenceSession(w, None)
-    else:  # TensorFlow models
-        import tensorflow as tf
-        if pb:  # https://www.tensorflow.org/guide/migrate#a_graphpb_or_graphpbtxt
-            def wrap_frozen_graph(gd, inputs, outputs):
-                x = tf.compat.v1.wrap_function(lambda: tf.compat.v1.import_graph_def(gd, name=""), [])  # wrapped import
-                return x.prune(tf.nest.map_structure(x.graph.as_graph_element, inputs),
-                               tf.nest.map_structure(x.graph.as_graph_element, outputs))
-
-            graph_def = tf.Graph().as_graph_def()
-            graph_def.ParseFromString(open(w, 'rb').read())
-            frozen_func = wrap_frozen_graph(gd=graph_def, inputs="x:0", outputs="Identity:0")
-        elif saved_model:
-            model = tf.keras.models.load_model(w)
-        elif tflite:
-            interpreter = tf.lite.Interpreter(model_path=w)  # load TFLite model
-            interpreter.allocate_tensors()  # allocate
-            input_details = interpreter.get_input_details()  # inputs
-            output_details = interpreter.get_output_details()  # outputs
-            int8 = input_details[0]['dtype'] == np.uint8  # is TFLite quantized uint8 model
-    imgsz = check_img_size(imgsz, s=stride)  # check image size
+        model.model.half() if half else model.model.float()
 
     # Dataloader
     if webcam:
         view_img = check_imshow()
         cudnn.benchmark = True  # set True to speed up constant image size inference
-        dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt)
+        dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt and not jit)
         bs = len(dataset)  # batch_size
     else:
-        dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt)
+        dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt and not jit)
         bs = 1  # batch_size
     vid_path, vid_writer = [None] * bs, [None] * bs
 
     # Run inference
     if pt and device.type != 'cpu':
-        model(torch.zeros(1, 3, *imgsz).to(device).type_as(next(model.parameters())))  # run once
+        model(torch.zeros(1, 3, *imgsz).to(device).type_as(next(model.model.parameters())))  # warmup
     dt, seen = [0.0, 0.0, 0.0], 0
-    for path, img, im0s, vid_cap, s in dataset:
+    for path, im, im0s, vid_cap, s in dataset:
         t1 = time_sync()
-        if onnx:
-            img = img.astype('float32')
-        else:
-            img = torch.from_numpy(img).to(device)
-            img = img.half() if half else img.float()  # uint8 to fp16/32
-        img /= 255.0  # 0 - 255 to 0.0 - 1.0
-        if len(img.shape) == 3:
-            img = img[None]  # expand for batch dim
+        im = torch.from_numpy(im).to(device)
+        im = im.half() if half else im.float()  # uint8 to fp16/32
+        im /= 255  # 0 - 255 to 0.0 - 1.0
+        if len(im.shape) == 3:
+            im = im[None]  # expand for batch dim
         t2 = time_sync()
         dt[0] += t2 - t1
 
         # Inference
-        if pt:
-            visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
-            pred = model(img, augment=augment, visualize=visualize)[0]
-        elif onnx:
-            if dnn:
-                net.setInput(img)
-                pred = torch.tensor(net.forward())
-            else:
-                pred = torch.tensor(session.run([session.get_outputs()[0].name], {session.get_inputs()[0].name: img}))
-        else:  # tensorflow model (tflite, pb, saved_model)
-            imn = img.permute(0, 2, 3, 1).cpu().numpy()  # image in numpy
-            if pb:
-                pred = frozen_func(x=tf.constant(imn)).numpy()
-            elif saved_model:
-                pred = model(imn, training=False).numpy()
-            elif tflite:
-                if int8:
-                    scale, zero_point = input_details[0]['quantization']
-                    imn = (imn / scale + zero_point).astype(np.uint8)  # de-scale
-                interpreter.set_tensor(input_details[0]['index'], imn)
-                interpreter.invoke()
-                pred = interpreter.get_tensor(output_details[0]['index'])
-                if int8:
-                    scale, zero_point = output_details[0]['quantization']
-                    pred = (pred.astype(np.float32) - zero_point) * scale  # re-scale
-            pred[..., 0] *= imgsz[1]  # x
-            pred[..., 1] *= imgsz[0]  # y
-            pred[..., 2] *= imgsz[1]  # w
-            pred[..., 3] *= imgsz[0]  # h
-            pred = torch.tensor(pred)
+        visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False
+        pred = model(im, augment=augment, visualize=visualize)
         t3 = time_sync()
         dt[1] += t3 - t2
 
@@ -181,8 +121,7 @@ def wrap_frozen_graph(gd, inputs, outputs):
         dt[2] += time_sync() - t3
 
         # Second-stage classifier (optional)
-        if classify:
-            pred = apply_classifier(pred, modelc, img, im0s)
+        # pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)
 
         # Process predictions
         for i, det in enumerate(pred):  # per image
@@ -194,15 +133,15 @@ def wrap_frozen_graph(gd, inputs, outputs):
                 p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0)
 
             p = Path(p)  # to Path
-            save_path = str(save_dir / p.name)  # img.jpg
-            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
+            save_path = str(save_dir / p.name)  # im.jpg
+            txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}')  # im.txt
+            s += '%gx%g ' % im.shape[2:]  # print string
             gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]  # normalization gain whwh
             imc = im0.copy() if save_crop else im0  # for save_crop
             annotator = Annotator(im0, line_width=line_thickness, example=str(names))
             if len(det):
                 # Rescale boxes from img_size to im0 size
-                det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()
+                det[:, :4] = scale_coords(im.shape[2:], det[:, :4], im0.shape).round()
 
                 # Print results
                 for c in det[:, -1].unique():