YOLOv5 AttributeError: ‘Upsample‘ object has no attribute ‘recompute_scale_factor‘

created at 03-20-2022 views: 299

error message

Traceback (most recent call last):
File “E:\yolo\yolov5-5.0\yolov5-5.0\detect.py”, line 72, in detect
pred = model(img, augment=opt.augment)[0]
File “D:\python\anaconda\lib\site-packages\torch\nn\modules\module.py”, line 1110, in _call_impl
return forward_call(*input, **kwargs)
File “E:\yolo\yolov5-5.0\yolov5-5.0\models\yolo.py”, line 123, in forward
return self.forward_once(x, profile) # single-scale inference, train
File “E:\yolo\yolov5-5.0\yolov5-5.0\models\yolo.py”, line 139, in forward_once
x = m(x) # run
File “D:\python\anaconda\lib\site-packages\torch\nn\modules\module.py”, line 1110, in _call_impl
return forward_call(*input, **kwargs)
File “D:\python\anaconda\lib\site-packages\torch\nn\modules\upsampling.py”, line 154, in forward
recompute_scale_factor=self.recompute_scale_factor)
File “D:\python\anaconda\lib\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’

solution

  1. torch version 1.11.0 torchvision version: 0.10.2
  2. Downgrade torchvision version: 0.10.1
  3. Downgrade torch version: 1.9.1
created at:03-20-2022
edited at: 05-31-2022: