Update app.py

app.py

@@ -7,18 +7,15 @@ from transformers import ViTImageProcessor,pipeline
 model = ViTImageProcessor.from_pretrained('SeyedAli/Food-Image-Classification-VIT')
 
 def FoodClassification(image):
-    image = read_image(image)
-    # Encode your PIL Image as a JPEG without writing to disk
-    # buffer = io.BytesIO(image)
-    # YourImage.save(buffer, format='JPEG', quality=75)
-
-    # # You probably want
-    # desiredObject = buffer.getbuffer()
-    
-    pipline = pipeline(task="image-classification", model=model)
-    #output=pipline(model(Image.open(desiredObject), return_tensors='pt'))
-    output=pipline(image, return_tensors='pt')
-    return output
+    with tempfile.NamedTemporaryFile(suffix=".png") as temp_audio_file:
+        # Copy the contents of the uploaded audio file to the temporary file
+        temp_image_file.write(open(image, "rb").read())
+        temp_image_file.flush()
+        # Load the image file using torchvision
+        image = read_image(temp_image_file.name)
+        pipline = pipeline(task="image-classification", model=model)
+        output=pipline(image, return_tensors='pt')
+            return output
 
 iface = gr.Interface(fn=FoodClassification, inputs="image", outputs="text")
 iface.launch(share=False)