AttributeError: ‘Upsample‘ object has no attribute ‘recompute_scale_factor‘

使用torch 1.11.0+cu102 CPU运行u版yolov5时报错：

Traceback (most recent call last):
  File "yolov5/detect.py", line 293, in <module>
    main(opt)
  File "yolov5/detect.py", line 288, in main
    run(**vars(opt))
  File "anaconda3/envs/yolov5/lib/python3.8/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "yolov5/detect.py", line 152, in run
    pred = model(img,
  File "anaconda3/envs/yolov5/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
    return forward_call(*input, **kwargs)
  File "yolov5/models/yolo.py", line 195, in forward
    return self.forward_once(x, profile, visualize)  # single-scale inference, train
  File "yolov5/models/yolo.py", line 226, in forward_once
    x = m(x)  # run
  File "anaconda3/envs/yolov5/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
    return forward_call(*input, **kwargs)
  File "anaconda3/envs/yolov5/lib/python3.8/site-packages/torch/nn/modules/upsampling.py", line 154, in forward
    recompute_scale_factor=self.recompute_scale_factor)
  File "anaconda3/envs/yolov5/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1185, in __getattr__
    raise AttributeError("'{}' object has no attribute '{}'".format(
AttributeError: 'Upsample' object has no attribute 'recompute_scale_factor'

Process finished with exit code 1

参考：http://www.manongjc.com/detail/28-llivmebvzwrvnfa.html
重新装pytorch

conda install pytorch==1.9.0 torchvision==0.10.0 torchaudio==0.9.0 cudatoolkit=10.2 -c pytorch