Refactor `export.py` (#4080)

export.py

@@ -24,74 +24,29 @@ from utils.general import colorstr, check_img_size, check_requirements, file_siz
 from utils.torch_utils import select_device
 
 
-def run(weights='./yolov5s.pt',  # weights path
-        img_size=(640, 640),  # image (height, width)
-        batch_size=1,  # batch size
-        device='cpu',  # cuda device, i.e. 0 or 0,1,2,3 or cpu
-        include=('torchscript', 'onnx', 'coreml'),  # include formats
-        half=False,  # FP16 half-precision export
-        inplace=False,  # set YOLOv5 Detect() inplace=True
-        train=False,  # model.train() mode
-        optimize=False,  # TorchScript: optimize for mobile
-        dynamic=False,  # ONNX: dynamic axes
-        simplify=False,  # ONNX: simplify model
-        opset_version=12,  # ONNX: opset version
-        ):
-    t = time.time()
-    include = [x.lower() for x in include]
-    img_size *= 2 if len(img_size) == 1 else 1  # expand
-
-    # Load PyTorch model
-    device = select_device(device)
-    assert not (device.type == 'cpu' and half), '--half only compatible with GPU export, i.e. use --device 0'
-    model = attempt_load(weights, map_location=device)  # load FP32 model
-    labels = model.names
-
-    # Input
-    gs = int(max(model.stride))  # grid size (max stride)
-    img_size = [check_img_size(x, gs) for x in img_size]  # verify img_size are gs-multiples
-    img = torch.zeros(batch_size, 3, *img_size).to(device)  # image size(1,3,320,192) iDetection
-
-    # Update model
-    if half:
-        img, model = img.half(), model.half()  # to FP16
-    model.train() if train else model.eval()  # training mode = no Detect() layer grid construction
-    for k, m in model.named_modules():
-        m._non_persistent_buffers_set = set()  # pytorch 1.6.0 compatibility
-        if isinstance(m, Conv):  # assign export-friendly activations
-            if isinstance(m.act, nn.Hardswish):
-                m.act = Hardswish()
-            elif isinstance(m.act, nn.SiLU):
-                m.act = SiLU()
-        elif isinstance(m, Detect):
-            m.inplace = inplace
-            m.onnx_dynamic = dynamic
-            # m.forward = m.forward_export  # assign forward (optional)
-
-    for _ in range(2):
-        y = model(img)  # dry runs
-    print(f"\n{colorstr('PyTorch:')} starting from {weights} ({file_size(weights):.1f} MB)")
-
-    # TorchScript export -----------------------------------------------------------------------------------------------
-    if 'torchscript' in include or 'coreml' in include:
+def export_torchscript(model, img, file, optimize):
+    # TorchScript model export
     prefix = colorstr('TorchScript:')
     try:
         print(f'\n{prefix} starting export with torch {torch.__version__}...')
-            f = weights.replace('.pt', '.torchscript.pt')  # filename
+        f = file.with_suffix('.torchscript.pt')
         ts = torch.jit.trace(model, img, strict=False)
         (optimize_for_mobile(ts) if optimize else ts).save(f)
         print(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
+        return ts
     except Exception as e:
         print(f'{prefix} export failure: {e}')
 
-    # ONNX export ------------------------------------------------------------------------------------------------------
-    if 'onnx' in include:
+
+def export_onnx(model, img, file, opset_version, train, dynamic, simplify):
+    # ONNX model export
     prefix = colorstr('ONNX:')
     try:
+        check_requirements(('onnx', 'onnx-simplifier'))
         import onnx
 
         print(f'{prefix} starting export with onnx {onnx.__version__}...')
-            f = weights.replace('.pt', '.onnx')  # filename
+        f = file.with_suffix('.onnx')
         torch.onnx.export(model, img, f, verbose=False, opset_version=opset_version,
                           training=torch.onnx.TrainingMode.TRAINING if train else torch.onnx.TrainingMode.EVAL,
                           do_constant_folding=not train,
@@ -109,7 +64,6 @@ def run(weights='./yolov5s.pt',  # weights path
         # Simplify
         if simplify:
             try:
-                    check_requirements(['onnx-simplifier'])
                 import onnxsim
 
                 print(f'{prefix} simplifying with onnx-simplifier {onnxsim.__version__}...')
@@ -125,21 +79,79 @@ def run(weights='./yolov5s.pt',  # weights path
     except Exception as e:
         print(f'{prefix} export failure: {e}')
 
-    # CoreML export ----------------------------------------------------------------------------------------------------
-    if 'coreml' in include:
+
+def export_coreml(ts_model, img, file, train):
+    # CoreML model export
     prefix = colorstr('CoreML:')
     try:
         import coremltools as ct
 
         print(f'{prefix} starting export with coremltools {ct.__version__}...')
+        f = file.with_suffix('.mlmodel')
         assert train, 'CoreML exports should be placed in model.train() mode with `python export.py --train`'
-            model = ct.convert(ts, inputs=[ct.ImageType('image', shape=img.shape, scale=1 / 255.0, bias=[0, 0, 0])])
-            f = weights.replace('.pt', '.mlmodel')  # filename
+        model = ct.convert(ts_model, inputs=[ct.ImageType('image', shape=img.shape, scale=1 / 255.0, bias=[0, 0, 0])])
         model.save(f)
         print(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
     except Exception as e:
         print(f'{prefix} export failure: {e}')
 
+
+def run(weights='./yolov5s.pt',  # weights path
+        img_size=(640, 640),  # image (height, width)
+        batch_size=1,  # batch size
+        device='cpu',  # cuda device, i.e. 0 or 0,1,2,3 or cpu
+        include=('torchscript', 'onnx', 'coreml'),  # include formats
+        half=False,  # FP16 half-precision export
+        inplace=False,  # set YOLOv5 Detect() inplace=True
+        train=False,  # model.train() mode
+        optimize=False,  # TorchScript: optimize for mobile
+        dynamic=False,  # ONNX: dynamic axes
+        simplify=False,  # ONNX: simplify model
+        opset_version=12,  # ONNX: opset version
+        ):
+    t = time.time()
+    include = [x.lower() for x in include]
+    img_size *= 2 if len(img_size) == 1 else 1  # expand
+    file = Path(weights)
+
+    # Load PyTorch model
+    device = select_device(device)
+    assert not (device.type == 'cpu' and half), '--half only compatible with GPU export, i.e. use --device 0'
+    model = attempt_load(weights, map_location=device)  # load FP32 model
+    names = model.names
+
+    # Input
+    gs = int(max(model.stride))  # grid size (max stride)
+    img_size = [check_img_size(x, gs) for x in img_size]  # verify img_size are gs-multiples
+    img = torch.zeros(batch_size, 3, *img_size).to(device)  # image size(1,3,320,192) iDetection
+
+    # Update model
+    if half:
+        img, model = img.half(), model.half()  # to FP16
+    model.train() if train else model.eval()  # training mode = no Detect() layer grid construction
+    for k, m in model.named_modules():
+        if isinstance(m, Conv):  # assign export-friendly activations
+            if isinstance(m.act, nn.Hardswish):
+                m.act = Hardswish()
+            elif isinstance(m.act, nn.SiLU):
+                m.act = SiLU()
+        elif isinstance(m, Detect):
+            m.inplace = inplace
+            m.onnx_dynamic = dynamic
+            # m.forward = m.forward_export  # assign forward (optional)
+
+    for _ in range(2):
+        y = model(img)  # dry runs
+    print(f"\n{colorstr('PyTorch:')} starting from {weights} ({file_size(weights):.1f} MB)")
+
+    # Exports
+    if 'onnx' in include:
+        export_onnx(model, img, file, opset_version, train, dynamic, simplify)
+    if 'torchscript' in include or 'coreml' in include:
+        ts = export_torchscript(model, img, file, optimize)
+        if 'coreml' in include:
+            export_coreml(ts, img, file, train)
+
     # Finish
     print(f'\nExport complete ({time.time() - t:.2f}s). Visualize with https://github.com/lutzroeder/netron.')