Skip to content
This repository has been archived by the owner on Oct 9, 2023. It is now read-only.

Fix normalizing video classification input #1213

Merged
merged 5 commits into from
Mar 3, 2022
Merged

Fix normalizing video classification input #1213

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
108abcd
add lambda function to normalize
dudeperf3ct Mar 2, 2022
8a48419
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Mar 2, 2022
23f22ac
remove lambda layer and replace function name
dudeperf3ct Mar 2, 2022
e02f35e
Update CHANGELOG.md
dudeperf3ct Mar 2, 2022
e8fa233
Merge branch 'master' into bugfix/video-input-normalize
ethanwharris Mar 3, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,8 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/).

### Fixed

- Fixed normalizing inputs to video classification ([#1213](https://github.com/PyTorchLightning/lightning-flash/pull/1213))

- Fixed examples (question answering), where NLTK's `punkt` module needs to be downloaded first. ([#1215](https://github.com/PyTorchLightning/lightning-flash/pull/1215/files))

- Fixed a bug where DDP would not work with Flash tasks ([#1182](https://github.com/PyTorchLightning/lightning-flash/pull/1182))
Expand Down
7 changes: 6 additions & 1 deletion flash/video/classification/input_transform.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,10 @@
ClipSampler, LabeledVideoDataset, EncodedVideo, ApplyTransformToKey = None, None, None, None


def normalize(x: torch.Tensor) -> torch.Tensor:
return x / 255.0


@requires("video")
@dataclass
class VideoClassificationInputTransform(InputTransform):
Expand All @@ -48,7 +52,8 @@ def per_sample_transform(self) -> Callable:
per_sample_transform = [CenterCrop(self.image_size)]

return ApplyToKeys(
"video", Compose([UniformTemporalSubsample(self.temporal_sub_sample)] + per_sample_transform)
"video",
Compose([UniformTemporalSubsample(self.temporal_sub_sample), normalize] + per_sample_transform),
)

def per_batch_transform_on_device(self) -> Callable:
Expand Down