Update app.py

app.py

@@ -24,10 +24,11 @@ dataset = load_dataset("jamescalam/unsplash-25k-photos", split="train")  # all 2
 height = 256   # height for resizing images
 
 def predict(image, labels):
-    inputs = processor(text=[f"a photo of {c}" for c in labels], images=image, return_tensors="pt", padding=True)
-    outputs = model(**inputs)
-    logits_per_image = outputs.logits_per_image # this is the image-text similarity score
-    probs = logits_per_image.softmax(dim=1) # we can take the softmax to get the label probabilities
+    with torch.no_grad():
+        inputs = processor(text=[f"a photo of {c}" for c in labels], images=image, return_tensors="pt", padding=True)
+        outputs = model(**inputs)
+        logits_per_image = outputs.logits_per_image # this is the image-text similarity score
+        probs = logits_per_image.softmax(dim=1).cpu().numpy() # we can take the softmax to get the label probabilities
     return {k: float(v) for k, v in zip(labels, probs[0])}