Fix the predictions returned by Trainer.predict(..)#641
Merged
Conversation
sararb
commented
Mar 10, 2023
| def forward( | ||
| self, inputs: TensorOrTabularData, targets=None, training=False, testing=False, **kwargs | ||
| ): | ||
| def forward(self, inputs: TabularData, targets=None, training=False, testing=False, **kwargs): |
Contributor
Author
There was a problem hiding this comment.
T4Rec only supports a dictionary of tensors (i.e. TabularData) as inputs.
sararb
commented
Mar 10, 2023
| torch.nn.Linear(input_size[-1], 1, bias=False), | ||
| torch.nn.Sigmoid(), | ||
| LambdaModule(lambda x: x.view(-1)), | ||
| LambdaModule(lambda x: torch.squeeze(x, -1)), |
Contributor
Author
There was a problem hiding this comment.
In the case of sequential binary classification, we need to keep the second dimension (i.e. sequence length)
Contributor
|
rerun tests |
rnyak
approved these changes
Mar 14, 2023
Documentation previewhttps://nvidia-merlin.github.io/Transformers4Rec/review/pr-641 |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes #636
Goals ⚽
Trainer.predict().predict_top_kcan only be applied to NextItemPredictionTask.Implementation Details 🚧
Testing Details 🔍
test_sequential_binary_classification_modelto test a sequential model trained with a per-item binary classification task.test_trainer_music_streamingtest_trainer_trop_k_with_wrong_taskto ensure the BC task cannot be used withpredict_top_k > 0