A view was created in no_grad mode and is being modified inplace with grad mode enabled. This view was created inside a custom Function (or because an input was returned as-is) and the autograd logic to handle view+inplace would override the custom backward associated with the custom Function, leading to incorrect gradients. This behavior is forbidden. You can fix this by cloning the output of the custom Function. #15
Traceback (most recent call last):
File "pretrain.py", line 240, in
main(arguments)
File "pretrain.py", line 177, in main
segs_S1,maskratio,,_= model_1(inputs_S1, patch_locations)
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, kwargs)
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/parallel/data_parallel.py", line 166, in forward
return self.module(*inputs[0], *kwargs[0])
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(input, kwargs)
File "/root/m3ae/model/Unet.py", line 830, in forward
x[l] = x[l] mask + self.limage[:, :, location[0][0][l]: location[0][1][l], location[1][0][l]: location[1][1][l], location[2][0][l]: location[2][1][l]] (1-mask) # not detach here
RuntimeError: A view was created in no_grad mode and is being modified inplace with grad mode enabled. This view was created inside a custom Function (or because an input was returned as-is) and the autograd logic to handle view+inplace would override the custom backward associated with the custom Function, leading to incorrect gradients. This behavior is forbidden. You can fix this by cloning the output of the custom Function.
yuyuyu13
commented
2 months ago
Traceback (most recent call last): File "pretrain.py", line 240, in
main(arguments)
File "pretrain.py", line 177, in main
segs_S1,maskratio,,_= model_1(inputs_S1, patch_locations)
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(*input, kwargs)
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/parallel/data_parallel.py", line 166, in forward
return self.module(*inputs[0], *kwargs[0])
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
return forward_call(input, kwargs)
File "/root/m3ae/model/Unet.py", line 830, in forward
x[l] = x[l] mask + self.limage[:, :, location[0][0][l]: location[0][1][l], location[1][0][l]: location[1][1][l], location[2][0][l]: location[2][1][l]] (1-mask) # not detach here
RuntimeError: A view was created in no_grad mode and is being modified inplace with grad mode enabled. This view was created inside a custom Function (or because an input was returned as-is) and the autograd logic to handle view+inplace would override the custom backward associated with the custom Function, leading to incorrect gradients. This behavior is forbidden. You can fix this by cloning the output of the custom Function.