Update timeseries_classification_transformer tutorial with good accuracy #2006
Conversation
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
fchollet
reviewed
Dec 18, 2024
|
|
||
| x = layers.GlobalAveragePooling1D(data_format="channels_last")(x) | ||
| print(f"Transformer Encoder: {x}") | ||
| x = layers.GlobalAveragePooling1D(data_format="channels_first")(x) |
There was a problem hiding this comment.
This is incorrect unfortunately? We should be pooling on the time dimension.
There was a problem hiding this comment.
@fchollet - As per code example earlier data_format="channels_last" reduces the model parameter and accuracy degradation on GPU in latest keras. data_format="channels_first" in pooling also reduce the number of time steps in same GPU environment and get good accuracy.
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Outdated suggestions cannot be applied.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.
timeseries_classification_transformer model creation data_format="channels_last" is giving less model parameters and degrades accuracy. Update example with data_format="channels_first". Fixes #20627