Search for both basic and bottleneck blocks (to fix "no known network structure detected" warning with ResNet-50 and other similar models) #2
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Currently when trying to use ResNet-50 (the same issue happens with usual
ResNeSt-50 and many other similar models) from timm library
https://github.com/rwightman/pytorch-image-models, I get the following warning:
"Manifold mixup: no known network structure detected, 126 modules will be used
for mixup"
This happens because ResNet-50 and higher do not have any BasicBlock and have
Bottlenecks instead. With this patch I get this message:
"Manifold mixup: Block structure detected, 16 modules will be used for mixup."
I get better error_rate than when 126 modules were used for mixup.