Open
Conversation
Add B6, B7 models and AutoAugment models
Thanks for this repo! Quick remark: I tried passing `efficientnet_b0` but you get `KeyError: 'efficientnet_b0'` if you try to pass this. Yet, if you pass a wrong model name such as `efficientnet_0` you get the following message. ``` ValueError: model_name should be one of: efficientnet_b0, efficientnet_b1, efficientnet_b2, efficientnet_b3, efficientnet_b4, efficientnet_b5, efficientnet_b6, efficientnet_b7 ``` The error should tell you to provide a name with a dash instead. ``` ValueError: model_name should be one of: efficientnet-b0, efficientnet-b1, efficientnet-b2, efficientnet-b3, efficientnet-b4, efficientnet-b5, efficientnet-b6, efficientnet-b7 ``` I think the proposed small change fixes the issue.
Improved inheritance support
Improved error messages
Updated ReLU, dropout, and more
…training) and standard swish function (for exporting).
Add memory-efficient and export-friendly swish activation functions
Fixes ``` efficientnet_pytorch/utils.py:45: DeprecationWarning: 'saved_variables' is deprecated; use 'saved_tensors' i = ctx.saved_variables[0] ```
Just to address the [reminder note](#91 (comment)) in issue #91.
Fix static padding calculation
Apply fix from #91 to README.md example
Hello, I think you miss one checkpoint given that endpoints['reduction_5'] is the head of the network but not the last layer of the backbone. This may be problematic if we use you implementation of EfficientNet as backbone of EfficientDet. In this PR, I let the checkpoint of the head (endpoints['reduction_6']) but changed endpoints['reduction_5'] accordingly. If I'm wrong let me know. Regards, Renaud
Link to efficientnet v2 paper was not working. So i just added it. A tiny contribution from my end.
Add Efficientnet v2 link in README.md
Minor improvements
Fix to accuracy function
Add new checkpoint
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
20 participants
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.
No description provided.