Update app.py

app.py

@@ -4,7 +4,7 @@ import pytesseract
 import yolov5
 
 from transformers import CLIPProcessor, CLIPModel
-model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
+vit_model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
 processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
 
 # load model
@@ -43,7 +43,7 @@ def zero_shot_classification(image, labels):
                        padding=True)
     print(type(inputs))
     print(inputs)
-    outputs = model(**inputs)
+    outputs = vit_model(**inputs)
     logits_per_image = outputs.logits_per_image # this is the image-text similarity score
     return logits_per_image.softmax(dim=1) # we can take the softmax to get the label probabilities