DeepStream 7.1 + Fixes + New model output format

utils/export_yoloV5.py

@@ -1,13 +1,9 @@
 import os
-import sys
-import argparse
-import warnings
 import onnx
 import torch
 import torch.nn as nn
+
 from models.experimental import attempt_load
-from utils.torch_utils import select_device
-from models.yolo import Detect
 
 
 class DeepStreamOutput(nn.Module):
@@ -17,46 +13,51 @@ class DeepStreamOutput(nn.Module):
     def forward(self, x):
         x = x[0]
         boxes = x[:, :, :4]
+        convert_matrix = torch.tensor(
+            [[1, 0, 1, 0], [0, 1, 0, 1], [-0.5, 0, 0.5, 0], [0, -0.5, 0, 0.5]], dtype=boxes.dtype, device=boxes.device
+        )
+        boxes @= convert_matrix
         objectness = x[:, :, 4:5]
-        scores, classes = torch.max(x[:, :, 5:], 2, keepdim=True)
+        scores, labels = torch.max(x[:, :, 5:], dim=-1, keepdim=True)
         scores *= objectness
-        classes = classes.float()
-        return boxes, scores, classes
+        return torch.cat([boxes, scores, labels.to(boxes.dtype)], dim=-1)
 
 
-def suppress_warnings():
-    warnings.filterwarnings('ignore', category=torch.jit.TracerWarning)
-    warnings.filterwarnings('ignore', category=UserWarning)
-    warnings.filterwarnings('ignore', category=DeprecationWarning)
-
-
-def yolov5_export(weights, device):
-    model = attempt_load(weights, device=device, inplace=True, fuse=True)
+def yolov5_export(weights, device, inplace=True, fuse=True):
+    model = attempt_load(weights, device=device, inplace=inplace, fuse=fuse)
     model.eval()
     for k, m in model.named_modules():
-        if isinstance(m, Detect):
+        if m.__class__.__name__ == 'Detect':
             m.inplace = False
             m.dynamic = False
             m.export = True
     return model
 
 
+def suppress_warnings():
+    import warnings
+    warnings.filterwarnings('ignore', category=torch.jit.TracerWarning)
+    warnings.filterwarnings('ignore', category=UserWarning)
+    warnings.filterwarnings('ignore', category=DeprecationWarning)
+    warnings.filterwarnings('ignore', category=FutureWarning)
+    warnings.filterwarnings('ignore', category=ResourceWarning)
+
+
 def main(args):
     suppress_warnings()
 
-    print('\nStarting: %s' % args.weights)
+    print(f'\nStarting: {args.weights}')
 
-    print('Opening YOLOv5 model\n')
+    print('Opening YOLOv5 model')
 
-    device = select_device('cpu')
+    device = torch.device('cpu')
     model = yolov5_export(args.weights, device)
 
     if len(model.names.keys()) > 0:
-        print('\nCreating labels.txt file')
-        f = open('labels.txt', 'w')
-        for name in model.names.values():
-            f.write(name + '\n')
-        f.close()
+        print('Creating labels.txt file')
+        with open('labels.txt', 'w', encoding='utf-8') as f:
+            for name in model.names.values():
+                f.write(f'{name}\n')
 
     model = nn.Sequential(model, DeepStreamOutput())
 
@@ -66,41 +67,37 @@ def main(args):
         img_size = [1280] * 2
 
     onnx_input_im = torch.zeros(args.batch, 3, *img_size).to(device)
-    onnx_output_file = os.path.basename(args.weights).split('.pt')[0] + '.onnx'
+    onnx_output_file = f'{args.weights}.onnx'
 
     dynamic_axes = {
         'input': {
             0: 'batch'
         },
-        'boxes': {
-            0: 'batch'
-        },
-        'scores': {
-            0: 'batch'
-        },
-        'classes': {
+        'output': {
             0: 'batch'
         }
     }
 
-    print('\nExporting the model to ONNX')
-    torch.onnx.export(model, onnx_input_im, onnx_output_file, verbose=False, opset_version=args.opset,
-                      do_constant_folding=True, input_names=['input'], output_names=['boxes', 'scores', 'classes'],
-                      dynamic_axes=dynamic_axes if args.dynamic else None)
+    print('Exporting the model to ONNX')
+    torch.onnx.export(
+        model, onnx_input_im, onnx_output_file, verbose=False, opset_version=args.opset, do_constant_folding=True,
+        input_names=['input'], output_names=['output'], dynamic_axes=dynamic_axes if args.dynamic else None
+    )
 
     if args.simplify:
         print('Simplifying the ONNX model')
-        import onnxsim
+        import onnxslim
         model_onnx = onnx.load(onnx_output_file)
-        model_onnx, _ = onnxsim.simplify(model_onnx)
+        model_onnx = onnxslim.slim(model_onnx)
         onnx.save(model_onnx, onnx_output_file)
 
-    print('Done: %s\n' % onnx_output_file)
+    print(f'Done: {onnx_output_file}\n')
 
 
 def parse_args():
+    import argparse
     parser = argparse.ArgumentParser(description='DeepStream YOLOv5 conversion')
-    parser.add_argument('-w', '--weights', required=True, help='Input weights (.pt) file path (required)')
+    parser.add_argument('-w', '--weights', required=True, type=str, help='Input weights (.pt) file path (required)')
     parser.add_argument('-s', '--size', nargs='+', type=int, default=[640], help='Inference size [H,W] (default [640])')
     parser.add_argument('--p6', action='store_true', help='P6 model')
     parser.add_argument('--opset', type=int, default=17, help='ONNX opset version')
@@ -117,4 +114,4 @@ def parse_args():
 
 if __name__ == '__main__':
     args = parse_args()
-    sys.exit(main(args))
+    main(args)