Concatenate last batches for batched inference #200
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
stes
requested changes
Nov 21, 2024
There was a problem hiding this comment.
Thanks, @CeliaBenquet . Can you add a test case which highlights the issue (and breaks in the "old" codebase), and then confirm that your fix passes the test?
stes
requested changes
Dec 17, 2024
Comment on lines
+1511
to
+1525
| def test_last_incomplete_batch_smaller_than_offset(): | ||
| """ | ||
| When offset of the model is larger than the remaining samples in the | ||
| last batch, an error could happen. We merge the penultimate | ||
| and last batches together to avoid this. | ||
| """ | ||
| train = cebra.data.TensorDataset(neural=np.random.rand(20111, 100), | ||
| continuous=np.random.rand(20111, 2)) | ||
|
|
||
| model = cebra.CEBRA(max_iterations=2, | ||
| model_architecture="offset36-model-more-dropout", | ||
| device="cpu") | ||
| model.fit(train.neural, train.continuous) | ||
|
|
||
| _ = model.transform(train.neural, batch_size=300) |
There was a problem hiding this comment.
What is the check here? i.e., what failed before the fix provided in this PR? It would be good to add some assert statement.
Is it required to do full model fitting for this to work, or would it be possible to explicitly test the newly added function?
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Outdated suggestions cannot be applied.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.
fix #199.
To still transform the extra samples that are not contained in a full batch while not getting an error regarding the next to last batch
batch_end_idxabove the length of the input, I propose to concatenate the penultimate batch (so the last complete batch) with the last batch (the incomplete batch from 1 tobatch_size).