a

app.py

@@ -37,7 +37,7 @@ def video_identity(video,user_name,class_name,trainortest,ready):
 
             def __call__(self, batch):
                 encodings = self.feature_extractor([x[0] for x in batch], return_tensors='pt')
-                encodings['labels'] = torch.tensor([x[1] for x in batch], dtype=torch.long)
+                encodings['labels'] = torch.tensor([x[1] for x in batch], dtype=torch.float)
                 return encodings 
         feature_extractor = ViTFeatureExtractor.from_pretrained('google/vit-base-patch16-224-in21k')
         model = ViTForImageClassification.from_pretrained(