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
The CRF class raises warning!
Could you kindly provide guidance on how to fix that? I modified the code a little, but still raises the warning. UserWarning: Mixed memory format inputs detected while calling the operator. The operator will output contiguous tensor even if some of the inputs are in channels_last format. (Triggered internally at /opt/conda/conda-bld/pytorch_1595629427478/work/aten/src/ATen/native/TensorIterator.cpp:918.)
The text was updated successfully, but these errors were encountered:
unfortunately, this implementation of CRF layer does not support the channels_last format of input tensor. Make sure that input tensor has size (N, C, H, W, ...), where N is batch size, C is number of segmentation classes, and (H, W, ...) is spatial size.
Dear @migonch ,
The CRF class raises warning!
Could you kindly provide guidance on how to fix that? I modified the code a little, but still raises the warning.
UserWarning: Mixed memory format inputs detected while calling the operator. The operator will output contiguous tensor even if some of the inputs are in channels_last format. (Triggered internally at /opt/conda/conda-bld/pytorch_1595629427478/work/aten/src/ATen/native/TensorIterator.cpp:918.)
The text was updated successfully, but these errors were encountered: