yolov5 导出LibTorch模型（CPU和GPU)

客官°小女子只卖身不卖艺 2023-01-16 09:44 317阅读 0赞

官方给出的是CPU：

"""Exports a YOLOv5 *.pt model to ONNX and TorchScript formats
    
    Usage:
        $ export PYTHONPATH="$PWD" && python models/export.py --weights ./weights/yolov5s.pt --img 640 --batch 1
    """
    
    import argparse
    
    import torch
    import torch.nn as nn
    
    import models
    from models.experimental import attempt_load
    from utils.activations import Hardswish
    from utils.general import set_logging
    
    if __name__ == '__main__':
        parser = argparse.ArgumentParser()
        parser.add_argument('--weights', type=str, default='../runs/exp7/weights/best.pt', help='weights path')  # from yolov5/models/
        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')
        opt = parser.parse_args()
        opt.img_size *= 2 if len(opt.img_size) == 1 else 1  # expand
        print(opt)
        set_logging()
    
        # Input
        img = torch.zeros((opt.batch_size, 3, *opt.img_size))  # image size(1,3,320,192) iDetection
    
        # Load PyTorch model
        model = attempt_load(opt.weights, map_location=torch.device('cpu'))  # load FP32 model
    
        # Update model
        for k, m in model.named_modules():
            m._non_persistent_buffers_set = set()  # pytorch 1.6.0 compatability
            if isinstance(m, models.common.Conv) and isinstance(m.act, nn.Hardswish):
                m.act = Hardswish()  # assign activation
            # if isinstance(m, models.yolo.Detect):
            #     m.forward = m.forward_export  # assign forward (optional)
        model.model[-1].export = True  # set Detect() layer export=True
        y = model(img)  # dry run
    
        # TorchScript export
        try:
            print('\nStarting TorchScript export with torch %s...' % torch.__version__)
            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)
        except Exception as e:
            print('TorchScript export failure: %s' % e)

GPU

import argparse
    
    import torch
    import torch.nn as nn
    
    import models
    from models.experimental import attempt_load
    from utils.activations import Hardswish
    from utils.general import set_logging
    
    if __name__ == '__main__':
        parser = argparse.ArgumentParser()
        parser.add_argument('--weights', type=str, default='../runs/exp7/weights/best.pt', help='weights path')  # from yolov5/models/
        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')
        opt = parser.parse_args()
        opt.img_size *= 2 if len(opt.img_size) == 1 else 1  # expand
        print(opt)
        set_logging()
    
        # Input
        img = torch.zeros((opt.batch_size, 3, *opt.img_size)).to(device='cuda')  # image size(1,3,320,192) iDetection
    
        # Load PyTorch model
        model = attempt_load(opt.weights, map_location=torch.device('cuda'))  # load FP32 model
    
        # Update model
        for k, m in model.named_modules():
            m._non_persistent_buffers_set = set()  # pytorch 1.6.0 compatability
            if isinstance(m, models.common.Conv) and isinstance(m.act, nn.Hardswish):
                m.act = Hardswish()  # assign activation
            # if isinstance(m, models.yolo.Detect):
            #     m.forward = m.forward_export  # assign forward (optional)
        model.model[-1].export = True  # set Detect() layer export=True
        y = model(img)  # dry run
    
        # TorchScript export
        try:
            print('\nStarting TorchScript export with torch %s...' % torch.__version__)
            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)
        except Exception as e:
            print('TorchScript export failure: %s' % e)