Feat 478 efficientnet and refactor cnn_architectures #620
Conversation
This file contains 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
created helper functions for reshaping # input channels into a Conv2d and # output nodes of a Linear (fully connected) layer. Refactored architecture definitions
torch.hub apparently expects argument pretrained=Bool Also, avoid downloading pre-trained weights in tests
torch.hub downloads cause 403 error on Github workflows. Trying the workaround suggested here: pytorch/pytorch#61755 (comment)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Resolves #478 by adding EfficientNet to cnn_architectures. Also refactors cnn_architectures to consistently re-use weights when possible when reshaping the input conv2d layer of a model and consistently re-shape a final fully connected layer using helper functions.
Note new behavior for reshaping first conv2d layer's number of channels