Pre-train notebook sets requires_grad = True for ReLU rather than the Linear layer.#3
Open
AliceSum wants to merge 2 commits into
Open
Pre-train notebook sets requires_grad = True for ReLU rather than the Linear layer.#3AliceSum wants to merge 2 commits into
AliceSum wants to merge 2 commits into
Conversation
AliceSum
changed the title
AliceSum
changed the title
…of classifier lay, instead of the relu. Signed-off-by: Jonathan Sum <777JonathanSum@gmail.com>
…available() else 'cpu')" I used cuda 0 because I only have one gpu. Signed-off-by: Jonathan Sum <777JonathanSum@gmail.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
It should be Model.classifier[0].requires_grad = True because the layer at index 0 is the linear layer. Index 1 is the ReLU layer which does not have trainable parameters.
I have retrained the small VGG notebook with Model.classifier[0].requires_grad = True. The end result is kind of the same. That is test accuracy is 78%, but the training accuracy is slightly higher than the original notebook.
