From 6a72b6e4bd60ffaa899b07ea7f656f63ad585806 Mon Sep 17 00:00:00 2001 From: Glenn Jocher Date: Wed, 9 Jun 2021 22:43:46 +0200 Subject: [PATCH] Refactor models/export.py arguments (#3564) * Refactor models/export.py arguments * cleanup * cleanup (cherry picked from commit 0e5cfdbea756716d5bbdfe6f3b26b2731e2facc4) --- models/export.py | 108 +++++++++++++++++++++++++++-------------------- 1 file changed, 63 insertions(+), 45 deletions(-) diff --git a/models/export.py b/models/export.py index c03770178829..6f8799e55593 100644 --- a/models/export.py +++ b/models/export.py @@ -1,4 +1,4 @@ -"""Exports a YOLOv5 *.pt model to TorchScript, ONNX, CoreML formats +"""Export a YOLOv5 *.pt model to TorchScript, ONNX, CoreML formats Usage: $ python path/to/models/export.py --weights yolov5s.pt --img 640 --batch 1 @@ -21,42 +21,39 @@ from utils.general import colorstr, check_img_size, check_requirements, file_size, set_logging from utils.torch_utils import select_device -if __name__ == '__main__': - parser = argparse.ArgumentParser() - parser.add_argument('--weights', type=str, default='./yolov5s.pt', help='weights path') - parser.add_argument('--img-size', nargs='+', type=int, default=[640, 640], help='image size') # height, width - parser.add_argument('--batch-size', type=int, default=1, help='batch size') - parser.add_argument('--device', default='cpu', help='cuda device, i.e. 0 or 0,1,2,3 or cpu') - parser.add_argument('--include', nargs='+', default=['torchscript', 'onnx', 'coreml'], help='include formats') - parser.add_argument('--half', action='store_true', help='FP16 half-precision export') - parser.add_argument('--inplace', action='store_true', help='set YOLOv5 Detect() inplace=True') - parser.add_argument('--train', action='store_true', help='model.train() mode') - parser.add_argument('--optimize', action='store_true', help='optimize TorchScript for mobile') # TorchScript-only - parser.add_argument('--dynamic', action='store_true', help='dynamic ONNX axes') # ONNX-only - parser.add_argument('--simplify', action='store_true', help='simplify ONNX model') # ONNX-only - parser.add_argument('--opset-version', type=int, default=12, help='ONNX opset version') # ONNX-only - opt = parser.parse_args() - opt.img_size *= 2 if len(opt.img_size) == 1 else 1 # expand - opt.include = [x.lower() for x in opt.include] - print(opt) - set_logging() + +def export(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(opt.device) - assert not (opt.device.lower() == 'cpu' and opt.half), '--half only compatible with GPU export, i.e. use --device 0' - model = attempt_load(opt.weights, map_location=device) # load FP32 model + device = select_device(device) + assert not (device.type == 'cpu' and opt.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) - opt.img_size = [check_img_size(x, gs) for x in opt.img_size] # verify img_size are gs-multiples - img = torch.zeros(opt.batch_size, 3, *opt.img_size).to(device) # image size(1,3,320,192) iDetection + 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 opt.half: + if half: img, model = img.half(), model.half() # to FP16 - model.train() if opt.train else model.eval() # training mode = no Detect() layer grid construction + 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, models.common.Conv): # assign export-friendly activations @@ -65,42 +62,42 @@ elif isinstance(m.act, nn.SiLU): m.act = SiLU() elif isinstance(m, models.yolo.Detect): - m.inplace = opt.inplace - m.onnx_dynamic = opt.dynamic + 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 {opt.weights} ({file_size(opt.weights):.1f} MB)") + print(f"\n{colorstr('PyTorch:')} starting from {weights} ({file_size(weights):.1f} MB)") # TorchScript export ----------------------------------------------------------------------------------------------- - if 'torchscript' in opt.include or 'coreml' in opt.include: + if 'torchscript' in include or 'coreml' in include: prefix = colorstr('TorchScript:') try: print(f'\n{prefix} starting export with torch {torch.__version__}...') - f = opt.weights.replace('.pt', '.torchscript.pt') # filename + f = weights.replace('.pt', '.torchscript.pt') # filename ts = torch.jit.trace(model, img, strict=False) - (optimize_for_mobile(ts) if opt.optimize else ts).save(f) + (optimize_for_mobile(ts) if optimize else ts).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}') # ONNX export ------------------------------------------------------------------------------------------------------ - if 'onnx' in opt.include: + if 'onnx' in include: prefix = colorstr('ONNX:') try: import onnx print(f'{prefix} starting export with onnx {onnx.__version__}...') - f = opt.weights.replace('.pt', '.onnx') # filename - torch.onnx.export(model, img, f, verbose=False, opset_version=opt.opset_version, - training=torch.onnx.TrainingMode.TRAINING if opt.train else torch.onnx.TrainingMode.EVAL, - do_constant_folding=not opt.train, + f = weights.replace('.pt', '.onnx') # filename + 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, input_names=['images'], output_names=['output'], dynamic_axes={'images': {0: 'batch', 2: 'height', 3: 'width'}, # shape(1,3,640,640) 'output': {0: 'batch', 1: 'anchors'} # shape(1,25200,85) - } if opt.dynamic else None) + } if dynamic else None) # Checks model_onnx = onnx.load(f) # load onnx model @@ -108,7 +105,7 @@ # print(onnx.helper.printable_graph(model_onnx.graph)) # print # Simplify - if opt.simplify: + if simplify: try: check_requirements(['onnx-simplifier']) import onnxsim @@ -116,8 +113,8 @@ print(f'{prefix} simplifying with onnx-simplifier {onnxsim.__version__}...') model_onnx, check = onnxsim.simplify( model_onnx, - dynamic_input_shape=opt.dynamic, - input_shapes={'images': list(img.shape)} if opt.dynamic else None) + dynamic_input_shape=dynamic, + input_shapes={'images': list(img.shape)} if dynamic else None) assert check, 'assert check failed' onnx.save(model_onnx, f) except Exception as e: @@ -127,15 +124,15 @@ print(f'{prefix} export failure: {e}') # CoreML export ---------------------------------------------------------------------------------------------------- - if 'coreml' in opt.include: + if 'coreml' in include: prefix = colorstr('CoreML:') try: import coremltools as ct print(f'{prefix} starting export with coremltools {ct.__version__}...') - assert opt.train, 'CoreML exports should be placed in model.train() mode with `python export.py --train`' + 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 = opt.weights.replace('.pt', '.mlmodel') # filename + f = weights.replace('.pt', '.mlmodel') # filename model.save(f) print(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)') except Exception as e: @@ -143,3 +140,24 @@ # Finish print(f'\nExport complete ({time.time() - t:.2f}s). Visualize with https://github.com/lutzroeder/netron.') + + +if __name__ == '__main__': + parser = argparse.ArgumentParser() + parser.add_argument('--weights', type=str, default='./yolov5s.pt', help='weights path') + parser.add_argument('--img-size', nargs='+', type=int, default=[640, 640], help='image (height, width)') + parser.add_argument('--batch-size', type=int, default=1, help='batch size') + parser.add_argument('--device', default='cpu', help='cuda device, i.e. 0 or 0,1,2,3 or cpu') + parser.add_argument('--include', nargs='+', default=['torchscript', 'onnx', 'coreml'], help='include formats') + parser.add_argument('--half', action='store_true', help='FP16 half-precision export') + parser.add_argument('--inplace', action='store_true', help='set YOLOv5 Detect() inplace=True') + parser.add_argument('--train', action='store_true', help='model.train() mode') + parser.add_argument('--optimize', action='store_true', help='TorchScript: optimize for mobile') + parser.add_argument('--dynamic', action='store_true', help='ONNX: dynamic axes') + parser.add_argument('--simplify', action='store_true', help='ONNX: simplify model') + parser.add_argument('--opset-version', type=int, default=12, help='ONNX: opset version') + opt = parser.parse_args() + print(opt) + set_logging() + + export(**vars(opt))