Update README.md

The sample code in the md file seems to have some problems, after this modification my side can run.

README.md

@@ -24,7 +24,7 @@ from transformers import AutoImageProcessor, TimesformerForVideoClassification
 import numpy as np
 import torch
 
-video = list(np.random.randn(8, 3, 224, 224))
+video = list(np.random.randn(8, 3, 224, 224).astype(np.uint8))
 
 processor = AutoImageProcessor.from_pretrained("facebook/timesformer-base-finetuned-k400")
 model = TimesformerForVideoClassification.from_pretrained("facebook/timesformer-base-finetuned-k400")