Update app.py

app.py

@@ -9,12 +9,18 @@ from transformers import TrainingArguments, Trainer
 from transformers import VideoMAEImageProcessor, VideoMAEForVideoClassification
 from torchvision.transforms import Compose
 from pytorchvideo.data.labeled_video_dataset import LabeledVideoDataset
-import pytorchvideo.data
-
-from pytorchvideo.data.transforms import (
+from pytorchvideo.transforms import (
+    ApplyTransformToKey,
+    Normalize,
+    RandomShortSideScale,
+    RemoveKey,
+    ShortSideScale,
     UniformTemporalSubsample,
+)
+
+from torchvision.transforms import (
+    Compose,
     Lambda,
-    Normalize,
     Resize,
 )
 
@@ -68,8 +74,9 @@ def run_inference(model, video):
         logits = outputs.logits
 
     return logits
-
+    
 model_name = "latif98/videomae-base-finetuned-isl-numbers_aug"
+image_processor = VideoMAEImageProcessor.from_pretrained(model_name)
 model = VideoMAEForVideoClassification.from_pretrained(model_name)