You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi, I added cornerpooling in our pytorch model. But it booms following warning. Do you know how to fix this issue?
[W Resize.cpp:19] Warning: An output with one or more elements was resized since it had shape [877], which does not match the required output shape [434].This behavior is deprecated, and in a future PyTorch release outputs will not be resized unless they have zero elements. You can explicitly reuse an out tensor t by resizing it, inplace, to zero elements with t.resize_(0). (function resize_output)
[W LegacyDefinitions.cpp:72] Warning: masked_scatter_ received a mask with dtype torch.uint8, this behavior is now deprecated,please use a mask with dtype torch.bool instead. (function masked_scatter__cuda)
[W LegacyDefinitions.cpp:28] Warning: masked_fill_ received a mask with dtype torch.uint8, this behavior is now deprecated,please use a mask with dtype torch.bool instead. (function masked_fill__cuda)
The text was updated successfully, but these errors were encountered:
icesohelrana
changed the title
Warning in cornerpooling in pytorch loss.bacward()
Warning when used cornerpooling in a model
Mar 27, 2021
Hi, I added cornerpooling in our pytorch model. But it booms following warning. Do you know how to fix this issue?
[W Resize.cpp:19] Warning: An output with one or more elements was resized since it had shape [877], which does not match the required output shape [434].This behavior is deprecated, and in a future PyTorch release outputs will not be resized unless they have zero elements. You can explicitly reuse an out tensor t by resizing it, inplace, to zero elements with t.resize_(0). (function resize_output)
[W LegacyDefinitions.cpp:72] Warning: masked_scatter_ received a mask with dtype torch.uint8, this behavior is now deprecated,please use a mask with dtype torch.bool instead. (function masked_scatter__cuda)
[W LegacyDefinitions.cpp:28] Warning: masked_fill_ received a mask with dtype torch.uint8, this behavior is now deprecated,please use a mask with dtype torch.bool instead. (function masked_fill__cuda)
The text was updated successfully, but these errors were encountered: