onnx_export.py

.github/workflows/greetings.yml

@@ -10,7 +10,7 @@ jobs:
       with:
         repo-token: ${{ secrets.GITHUB_TOKEN }}
         pr-message: 'Hello @${{ github.actor }}, thank you for submitting a PR! We will respond as soon as possible.'
-        issue-message: >
+        issue-message: |
           Hello @${{ github.actor }}, thank you for your interest in our work! Please visit our [Custom Training Tutorial](https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data) to get started, and see our [Google Colab Notebook](https://github.com/ultralytics/yolov5/blob/master/tutorial.ipynb), [Docker Image](https://hub.docker.com/r/ultralytics/yolov5), and [GCP Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/GCP-Quickstart) for example environments.
             
           If this is a bug report, please provide screenshots and **minimum viable code to reproduce your issue**, otherwise we can not help you.

README.md

@@ -108,4 +108,4 @@ To access an up-to-date working environment (with all dependencies including CUD
 
 ## Contact
 
-**Issues should be raised directly in the repository.** For business inquiries or professional support requests please visit us at https://www.ultralytics.com.
+**Issues should be raised directly in the repository.** For business inquiries or professional support requests please visit https://www.ultralytics.com or email Glenn Jocher at glenn.jocher@ultralytics.com. 

detect.py

@@ -7,12 +7,12 @@ ONNX_EXPORT = False
 
 
 def detect(save_img=False):
-    imgsz = (320, 192) if ONNX_EXPORT else opt.img_size  # (320, 192) or (416, 256) or (608, 352) for (height, width)
-    out, source, weights, half, view_img, save_txt = opt.output, opt.source, opt.weights, opt.half, opt.view_img, opt.save_txt
+    out, source, weights, half, view_img, save_txt, imgsz = \
+        opt.output, opt.source, opt.weights, opt.half, opt.view_img, opt.save_txt, opt.img_size
     webcam = source == '0' or source.startswith('rtsp') or source.startswith('http') or source.endswith('.txt')
 
     # Initialize
-    device = torch_utils.select_device(device='cpu' if ONNX_EXPORT else opt.device)
+    device = torch_utils.select_device(opt.device)
     if os.path.exists(out):
         shutil.rmtree(out)  # delete output folder
     os.makedirs(out)  # make new output folder
@@ -35,20 +35,6 @@ def detect(save_img=False):
     # Fuse Conv2d + BatchNorm2d layers
     # model.fuse()
 
-    # Export mode
-    if ONNX_EXPORT:
-        model.fuse()
-        img = torch.zeros((1, 3) + imgsz)  # (1, 3, 320, 192)
-        f = opt.weights.replace(opt.weights.split('.')[-1], 'onnx')  # *.onnx filename
-        torch.onnx.export(model, img, f, verbose=False, opset_version=11)
-
-        # Validate exported model
-        import onnx
-        model = onnx.load(f)  # Load the ONNX model
-        onnx.checker.check_model(model)  # Check that the IR is well formed
-        print(onnx.helper.printable_graph(model.graph))  # Print a human readable representation of the graph
-        return
-
     # Half precision
     half = half and device.type != 'cpu'  # half precision only supported on CUDA
     if half:

models/onnx_export.py

+import argparse
+
+import onnx
+
+from models.common import *
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--weights', default='../weights/yolov5s.pt', help='model path RELATIVE to ./models/')
+    parser.add_argument('--img-size', default=640, help='inference size (pixels)')
+    parser.add_argument('--batch-size', default=1, help='batch size')
+    opt = parser.parse_args()
+
+    # Parameters
+    f = opt.weights.replace('.pt', '.onnx')  # onnx filename
+    img = torch.zeros((opt.batch_size, 3, opt.img_size, opt.img_size))  # image size, (1, 3, 320, 192) iDetection
+
+    # Load pytorch model
+    google_utils.attempt_download(opt.weights)
+    model = torch.load(opt.weights)['model']
+    model.eval()
+    # model.fuse()  # optionally fuse Conv2d + BatchNorm2d layers TODO
+
+    # Export to onnx
+    model.model[-1].export = True  # set Detect() layer export=True
+    torch.onnx.export(model, img, f, verbose=False, opset_version=11)
+
+    # Check onnx model
+    model = onnx.load(f)  # load onnx model
+    onnx.checker.check_model(model)  # check onnx model
+    print(onnx.helper.printable_graph(model.graph))  # print a human readable representation of the graph
+    print('Export complete. ONNX model saved to %s\nView with https://github.com/lutzroeder/netron' % f)