Fix normalizing video classification input (#1213)

Co-authored-by: Ethan Harris <ethanwharris@gmail.com>

CHANGELOG.md

@@ -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))

flash/video/classification/input_transform.py

@@ -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):
@@ -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: