Fix Inception model to match Tensorflow's FID Inception model #16
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
This change adapts the weights used by the model to the ones in the original Tensorflow implementation. The Inception weights available in torchvision do not correspond to the ones used by Tensorflow's FID. Furthermore, some subtle differences in the model implementation were changed to now match the Tensorflow implementation.
This was referenced May 27, 2019
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Outdated suggestions cannot be applied.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.
This change adapts the weights used by the model to the ones in the
original Tensorflow implementation. The Inception weights available in
torchvision do not correspond to the ones used by Tensorflow's FID.
Furthermore, some subtle differences in the model implementation were
changed to now match the Tensorflow implementation.
Overall, I now verified that the two models give exactly the same results when inputting exactly the same input image. This leaves different image loaders and interpolation algorithms as a possible source of introducing error. I also have not tested how the behavior on GPU is.