Open krteyu opened 3 months ago
This problem appears to be due to cbam being instantiated in edge extract but not being used in the forward function. Commenting out cbam appears to fix this issue.
However I am now getting an assert len(set(num_channels_list)) == 1
AssertionError similar to #4160 which is also open. I am not able to find the model dependency causing this issue, any help would be appreciated
Describe the bug: I am attempting to run this pruned mirror detection model [https://github.com/memgonzales/mirror-segmentation], but when I attempt to perform speedup_model(), I get the following error:
This error occurs for the mask element
edge_extract.cbam.ChannelGate.mlp.1
. Given below is the model description for this module:Environment:
Reproduce the problem
Code|Example: Model weights can be downloaded at https://drive.google.com/file/d/18zsqjK1aHVC4D8Ky530C--fwxdQylQ37/view?usp=sharing clone the above mentioned github and add the following to the main function of
prune.py
: