fix tests, small optimization to json dataset loading #241
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
neph1
commented
Jan 23, 2025
Comment on lines
+144
to
+147
| try: | ||
| video = self._preprocess_video(video_path) | ||
| except: | ||
| raise ValueError(f"Exception while preprocessing {video_path}.") |
There was a problem hiding this comment.
This was added for personal reasons, as I had difficulties finding out which file was causing issues
neph1
commented
Jan 23, 2025
| @@ -249,8 +258,6 @@ class ImageOrVideoDatasetWithResizing(ImageOrVideoDataset): | |||
| def __init__(self, *args, **kwargs) -> None: | |||
| super().__init__(*args, **kwargs) | |||
|
|
|||
| self.max_num_frames = max(self.resolution_buckets, key=lambda x: x[0])[0] | |||
neph1
commented
Jan 23, 2025
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Outdated suggestions cannot be applied.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 fixes the dataset tests that were referencing the old cogvideox repo.
I also noticed while doing so that using ImageOrVideoDataset directly will throw an exception because max_num_frames is not set. So I moved that to init of the base class.
There's also a minor refactor to the _load_dataset_from_json method, because I initially read it wrong and thought it was parsing two columns separately. At least it only parses the data once.
I still haven't done any test run with this. So maybe let it simmer for a bit.
Ref: #239