Merge branch 'master' of https://github.com/ultralytics/yolov5 into f…

…eature/DDP_fixed

.github/ISSUE_TEMPLATE/-question.md

@@ -0,0 +1,13 @@
+---
+name: "❓Question"
+about: Ask a general question
+title: ''
+labels: question
+assignees: ''
+
+---
+
+## ❔Question
+
+
+## Additional context

Dockerfile

@@ -25,10 +25,10 @@ COPY . /usr/src/app
 # t=ultralytics/yolov5:latest && sudo docker build -t $t . && sudo docker push $t
 
 # Pull and Run
-# t=ultralytics/yolov5:latest && sudo docker pull $t && sudo docker run -it --ipc=host $t bash
+# t=ultralytics/yolov5:latest && sudo docker pull $t && sudo docker run -it --ipc=host $t
 
 # Pull and Run with local directory access
-# t=ultralytics/yolov5:latest && sudo docker pull $t && sudo docker run -it --ipc=host --gpus all -v "$(pwd)"/coco:/usr/src/coco $t bash
+# t=ultralytics/yolov5:latest && sudo docker pull $t && sudo docker run -it --ipc=host --gpus all -v "$(pwd)"/coco:/usr/src/coco $t
 
 # Kill all
 # sudo docker kill "$(sudo docker ps -q)"

README.md

@@ -21,7 +21,7 @@ This repository represents Ultralytics open-source research into future object d
 | [YOLOv5m](https://drive.google.com/open?id=1Drs_Aiu7xx6S-ix95f9kNsA6ueKRpN2J)    | 43.4     | 43.4     | 62.4     | 3.0ms     | 333     || 21.8M  | 39.4B
 | [YOLOv5l](https://drive.google.com/open?id=1Drs_Aiu7xx6S-ix95f9kNsA6ueKRpN2J)    | 46.6     | 46.7     | 65.4     | 3.9ms     | 256     || 47.8M  | 88.1B
 | [YOLOv5x](https://drive.google.com/open?id=1Drs_Aiu7xx6S-ix95f9kNsA6ueKRpN2J)    | **48.4** | **48.4** | **66.9** | 6.1ms     | 164     || 89.0M  | 166.4B
-| [YOLOv3-SPP](https://drive.google.com/open?id=1Drs_Aiu7xx6S-ix95f9kNsA6ueKRpN2J)  | 45.6     | 45.5     | 65.2     | 4.5ms     | 222     || 63.0M  | 118.0B
+| [YOLOv3-SPP](https://drive.google.com/open?id=1Drs_Aiu7xx6S-ix95f9kNsA6ueKRpN2J) | 45.6     | 45.5     | 65.2     | 4.5ms     | 222     || 63.0M  | 118.0B
 
 
 ** AP<sup>test</sup> denotes COCO [test-dev2017](http://cocodataset.org/#upload) server results, all other AP results in the table denote val2017 accuracy.  
@@ -54,10 +54,11 @@ $ pip install -U -r requirements.txt
 
 Inference can be run on most common media formats. Model [checkpoints](https://drive.google.com/open?id=1Drs_Aiu7xx6S-ix95f9kNsA6ueKRpN2J) are downloaded automatically if available. Results are saved to `./inference/output`.
 ```bash
-$ python detect.py --source file.jpg  # image 
+$ python detect.py --source 0  # webcam
+                            file.jpg  # image 
                             file.mp4  # video
-                            ./dir  # directory
-                            0  # webcam
+                            path/  # directory
+                            path/*.jpg  # glob
                             rtsp://170.93.143.139/rtplive/470011e600ef003a004ee33696235daa  # rtsp stream
                             http://112.50.243.8/PLTV/88888888/224/3221225900/1.m3u8  # http stream
 ```
@@ -93,10 +94,11 @@ $ python train.py --data coco.yaml --cfg yolov5s.yaml --weights '' --batch-size
 
 ## Reproduce Our Environment
 
-To access an up-to-date working environment (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled), consider a:
+YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including CUDA/CUDNN, Python and PyTorch preinstalled):
 
-- **Google Cloud** Deep Learning VM with $300 free credit offer: See our [GCP Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/GCP-Quickstart) 
-- **Google Colab Notebook** with 12 hours of free GPU time. <a href="https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>
+- **Google Colab Notebook** with free GPU: <a href="https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"></a>
+- **Kaggle Notebook** with free GPU: [https://www.kaggle.com/ultralytics/yolov5](https://www.kaggle.com/ultralytics/yolov5)
+- **Google Cloud** Deep Learning VM. See [GCP Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/GCP-Quickstart) 
 - **Docker Image** https://hub.docker.com/r/ultralytics/yolov5. See [Docker Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/Docker-Quickstart) ![Docker Pulls](https://img.shields.io/docker/pulls/ultralytics/yolov5?logo=docker)
 
 

data/coco.yaml

@@ -1,13 +1,13 @@
 # COCO 2017 dataset http://cocodataset.org
 # Download command: bash yolov5/data/get_coco2017.sh
-# Train command: python train.py --data ./data/coco.yaml
-# Dataset should be placed next to yolov5 folder:
+# Train command: python train.py --data coco.yaml
+# Default dataset location is next to /yolov5:
 #   /parent_folder
 #     /coco
 #     /yolov5
 
 
-# train and val datasets (image directory or *.txt file with image paths)
+# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
 train: ../coco/train2017.txt  # 118k images
 val: ../coco/val2017.txt  # 5k images
 test: ../coco/test-dev2017.txt  # 20k images for submission to https://competitions.codalab.org/competitions/20794

data/coco128.yaml

@@ -1,15 +1,15 @@
 # COCO 2017 dataset http://cocodataset.org - first 128 training images
-# Download command:  python -c "from yolov5.utils.google_utils import gdrive_download; gdrive_download('1n_oKgR81BJtqk75b00eAjdv03qVCQn2f','coco128.zip')"
-# Train command: python train.py --data ./data/coco128.yaml
-# Dataset should be placed next to yolov5 folder:
+# Download command:  python -c "from yolov5.utils.google_utils import *; gdrive_download('1n_oKgR81BJtqk75b00eAjdv03qVCQn2f', 'coco128.zip')"
+# Train command: python train.py --data coco128.yaml
+# Default dataset location is next to /yolov5:
 #   /parent_folder
 #     /coco128
 #     /yolov5
 
 
-# train and val datasets (image directory or *.txt file with image paths)
-train: ../coco128/images/train2017/
-val: ../coco128/images/train2017/
+# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
+train: ../coco128/images/train2017/  # 128 images
+val: ../coco128/images/train2017/  # 128 images
 
 # number of classes
 nc: 80

data/get_coco2017.sh

@@ -1,12 +1,13 @@
 #!/bin/bash
 # COCO 2017 dataset http://cocodataset.org
 # Download command: bash yolov5/data/get_coco2017.sh
-# Train command: python train.py --data ./data/coco.yaml
-# Dataset should be placed next to yolov5 folder:
+# Train command: python train.py --data coco.yaml
+# Default dataset location is next to /yolov5:
 #   /parent_folder
 #     /coco
 #     /yolov5
 
+
 # Download labels from Google Drive, accepting presented query
 filename="coco2017labels.zip"
 fileid="1cXZR_ckHki6nddOmcysCuuJFM--T-Q6L"

data/get_voc.sh

@@ -1,11 +1,12 @@
 # PASCAL VOC dataset http://host.robots.ox.ac.uk/pascal/VOC/
 # Download command: bash ./data/get_voc.sh
 # Train command: python train.py --data voc.yaml
-# Dataset should be placed next to yolov5 folder:
+# Default dataset location is next to /yolov5:
 #   /parent_folder
 #     /VOC
 #     /yolov5
 
+
 start=`date +%s`
 
 # handle optional download dir

data/voc.yaml

@@ -1,14 +1,15 @@
 # PASCAL VOC dataset http://host.robots.ox.ac.uk/pascal/VOC/
 # Download command: bash ./data/get_voc.sh
 # Train command: python train.py --data voc.yaml
-# Dataset should be placed next to yolov5 folder:
+# Default dataset location is next to /yolov5:
 #   /parent_folder
 #     /VOC
 #     /yolov5
 
-# train and val datasets (image directory or *.txt file with image paths)
-train: ../VOC/images/train/
-val: ../VOC/images/val/
+
+# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
+train: ../VOC/images/train/  # 16551 images
+val: ../VOC/images/val/  # 4952 images
 
 # number of classes
 nc: 20

detect.py

@@ -2,7 +2,7 @@
 
 import torch.backends.cudnn as cudnn
 
-from utils import google_utils
+from models.experimental import *
 from utils.datasets import *
 from utils.utils import *
 
@@ -20,8 +20,7 @@ def detect(save_img=False):
     half = device.type != 'cpu'  # half precision only supported on CUDA
 
     # Load model
-    google_utils.attempt_download(weights)
-    model = torch.load(weights, map_location=device)['model'].float().eval()  # load FP32 model
+    model = attempt_load(weights, map_location=device)  # load FP32 model
     imgsz = check_img_size(imgsz, s=model.stride.max())  # check img_size
     if half:
         model.half()  # to FP16
@@ -129,15 +128,15 @@ def detect(save_img=False):
 
     if save_txt or save_img:
         print('Results saved to %s' % os.getcwd() + os.sep + out)
-        if platform == 'darwin':  # MacOS
+        if platform == 'darwin' and not opt.update:  # MacOS
             os.system('open ' + save_path)
 
     print('Done. (%.3fs)' % (time.time() - t0))
 
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser()
-    parser.add_argument('--weights', type=str, default='weights/yolov5s.pt', help='model.pt path')
+    parser.add_argument('--weights', nargs='+', type=str, default='yolov5s.pt', help='model.pt path(s)')
     parser.add_argument('--source', type=str, default='inference/images', help='source')  # file/folder, 0 for webcam
     parser.add_argument('--output', type=str, default='inference/output', help='output folder')  # output folder
     parser.add_argument('--img-size', type=int, default=640, help='inference size (pixels)')
@@ -146,7 +145,7 @@ def detect(save_img=False):
     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')
-    parser.add_argument('--classes', nargs='+', type=int, help='filter by class')
+    parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --class 0, or --class 0 2 3')
     parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
     parser.add_argument('--augment', action='store_true', help='augmented inference')
     parser.add_argument('--update', action='store_true', help='update all models')

hubconf.py

@@ -28,14 +28,18 @@ def create(name, pretrained, channels, classes):
         pytorch model
     """
     config = os.path.join(os.path.dirname(__file__), 'models', '%s.yaml' % name)  # model.yaml path
-    model = Model(config, channels, classes)
-    if pretrained:
-        ckpt = '%s.pt' % name  # checkpoint filename
-        google_utils.attempt_download(ckpt)  # download if not found locally
-        state_dict = torch.load(ckpt, map_location=torch.device('cpu'))['model'].float().state_dict()  # to FP32
-        state_dict = {k: v for k, v in state_dict.items() if model.state_dict()[k].shape == v.shape}  # filter
-        model.load_state_dict(state_dict, strict=False)  # load
-    return model
+    try:
+        model = Model(config, channels, classes)
+        if pretrained:
+            ckpt = '%s.pt' % name  # checkpoint filename
+            google_utils.attempt_download(ckpt)  # download if not found locally
+            state_dict = torch.load(ckpt, map_location=torch.device('cpu'))['model'].float().state_dict()  # to FP32
+            state_dict = {k: v for k, v in state_dict.items() if model.state_dict()[k].shape == v.shape}  # filter
+            model.load_state_dict(state_dict, strict=False)  # load
+        return model
+    except Exception as e:
+        help_url = 'https://github.com/ultralytics/yolov5/issues/36'
+        print('%s\nCache maybe be out of date. Delete cache and retry. See %s for help.' % (e, help_url))
 
 
 def yolov5s(pretrained=False, channels=3, classes=80):

models/experimental.py

@@ -1,6 +1,7 @@
 # This file contains experimental modules
 
 from models.common import *
+from utils import google_utils
 
 
 class CrossConv(nn.Module):
@@ -118,4 +119,23 @@ def forward(self, x, augment=False):
         y = []
         for module in self:
             y.append(module(x, augment)[0])
-        return torch.cat(y, 1), None  # ensembled inference output, train output
+        # y = torch.stack(y).max(0)[0]  # max ensemble
+        # y = torch.cat(y, 1)  # nms ensemble
+        y = torch.stack(y).mean(0)  # mean ensemble
+        return y, None  # inference, train output
+
+
+def attempt_load(weights, map_location=None):
+    # Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a
+    model = Ensemble()
+    for w in weights if isinstance(weights, list) else [weights]:
+        google_utils.attempt_download(w)
+        model.append(torch.load(w, map_location=map_location)['model'].float().fuse().eval())  # load FP32 model
+
+    if len(model) == 1:
+        return model[-1]  # return model
+    else:
+        print('Ensemble created with %s\n' % weights)
+        for k in ['names', 'stride']:
+            setattr(model, k, getattr(model[-1], k))
+        return model  # return ensemble

models/export.py

@@ -31,7 +31,7 @@
     # TorchScript export
     try:
         print('\nStarting TorchScript export with torch %s...' % torch.__version__)
-        f = opt.weights.replace('.pt', '.torchscript')  # filename
+        f = opt.weights.replace('.pt', '.torchscript.pt')  # filename
         ts = torch.jit.trace(model, img)
         ts.save(f)
         print('TorchScript export success, saved as %s' % f)
@@ -61,7 +61,8 @@
         import coremltools as ct
 
         print('\nStarting CoreML export with coremltools %s...' % ct.__version__)
-        model = ct.convert(ts, inputs=[ct.ImageType(name='images', shape=img.shape)])  # convert
+        # convert model from torchscript and apply pixel scaling as per detect.py
+        model = ct.convert(ts, inputs=[ct.ImageType(name='images', shape=img.shape, scale=1 / 255.0, bias=[0, 0, 0])])
         f = opt.weights.replace('.pt', '.mlmodel')  # filename
         model.save(f)
         print('CoreML export success, saved as %s' % f)

models/yolo.py

@@ -1,4 +1,5 @@
 import argparse
+from copy import deepcopy
 
 from models.experimental import *
 
@@ -43,20 +44,21 @@ def _make_grid(nx=20, ny=20):
 
 
 class Model(nn.Module):
-    def __init__(self, model_cfg='yolov5s.yaml', ch=3, nc=None):  # model, input channels, number of classes
+    def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None):  # model, input channels, number of classes
         super(Model, self).__init__()
-        if type(model_cfg) is dict:
-            self.md = model_cfg  # model dict
+        if isinstance(cfg, dict):
+            self.yaml = cfg  # model dict
         else:  # is *.yaml
             import yaml  # for torch hub
-            with open(model_cfg) as f:
-                self.md = yaml.load(f, Loader=yaml.FullLoader)  # model dict
+            self.yaml_file = Path(cfg).name
+            with open(cfg) as f:
+                self.yaml = yaml.load(f, Loader=yaml.FullLoader)  # model dict
 
         # Define model
-        if nc and nc != self.md['nc']:
-            print('Overriding %s nc=%g with nc=%g' % (model_cfg, self.md['nc'], nc))
-            self.md['nc'] = nc  # override yaml value
-        self.model, self.save = parse_model(self.md, ch=[ch])  # model, savelist, ch_out
+        if nc and nc != self.yaml['nc']:
+            print('Overriding %s nc=%g with nc=%g' % (cfg, self.yaml['nc'], nc))
+            self.yaml['nc'] = nc  # override yaml value
+        self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch])  # model, savelist, ch_out
         # print([x.shape for x in self.forward(torch.zeros(1, ch, 64, 64))])
 
         # Build strides, anchors
@@ -72,8 +74,7 @@ def __init__(self, model_cfg='yolov5s.yaml', ch=3, nc=None):  # model, input cha
 
         # Init weights, biases
         torch_utils.initialize_weights(self)
-        self._initialize_biases()  # only run once
-        torch_utils.model_info(self)
+        self.info()
         print('')
 
     def forward(self, x, augment=False, profile=False):
@@ -148,17 +149,21 @@ def fuse(self):  # fuse model Conv2d() + BatchNorm2d() layers
                 m.conv = torch_utils.fuse_conv_and_bn(m.conv, m.bn)  # update conv
                 m.bn = None  # remove batchnorm
                 m.forward = m.fuseforward  # update forward
-        torch_utils.model_info(self)
+        self.info()
         return self
 
-def parse_model(md, ch):  # model_dict, input_channels(3)
+    def info(self):  # print model information
+        torch_utils.model_info(self)
+
+
+def parse_model(d, ch):  # model_dict, input_channels(3)
     print('\n%3s%18s%3s%10s  %-40s%-30s' % ('', 'from', 'n', 'params', 'module', 'arguments'))
-    anchors, nc, gd, gw = md['anchors'], md['nc'], md['depth_multiple'], md['width_multiple']
+    anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
     na = (len(anchors[0]) // 2)  # number of anchors
     no = na * (nc + 5)  # number of outputs = anchors * (classes + 5)
 
     layers, save, c2 = [], [], ch[-1]  # layers, savelist, ch out
-    for i, (f, n, m, args) in enumerate(md['backbone'] + md['head']):  # from, number, module, args
+    for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']):  # from, number, module, args
         m = eval(m) if isinstance(m, str) else m  # eval strings
         for j, a in enumerate(args):
             try:

requirements.txt

@@ -2,7 +2,7 @@
 Cython
 numpy==1.17
 opencv-python
-torch>=1.4
+torch>=1.5.1
 matplotlib
 pillow
 tensorboard