fix: TCN model predict crash on single-sample final batch#2172
Open
EdenRochmanSharabi wants to merge 1 commit intomicrosoft:mainfrom
Open
fix: TCN model predict crash on single-sample final batch#2172EdenRochmanSharabi wants to merge 1 commit intomicrosoft:mainfrom
EdenRochmanSharabi wants to merge 1 commit intomicrosoft:mainfrom
Conversation
When the final batch has a single sample, model output becomes a 0-d numpy array after .cpu().numpy(). np.concatenate cannot mix 0-d and 1-d arrays, causing a crash. Wrap with np.atleast_1d() before appending to preds list. Fixes microsoft#1752
Author
|
@microsoft-github-policy-service agree |
EdenRochmanSharabi
changed the title
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Fixes #1752
When the inference dataset size is not evenly divisible by batch size, the last batch has 1 sample.
squeeze()produces a 0-d tensor, and after.numpy(),np.concatenatefails because it cannot concatenate 0-d arrays with 1-d arrays.Changes
qlib/contrib/model/pytorch_tcn_ts.py: Wrapped prediction output withnp.atleast_1d()before appending to the results listtests/test_tcn_single_sample_batch.py: Tests verifying concatenation works with mixed array dimensions