Update app.py

app.py

@@ -8,8 +8,9 @@ model, preprocess = clip.load("ViT-B/32", device=device)
 
 def clip(image, text):
 
+    text = text.split(",")
     image = preprocess(image).unsqueeze(0).to(device)
-    text = clip.tokenize([text]).to(device)
+    text = clip.tokenize(text).to(device)
 
     with torch.no_grad():
         image_features = model.encode_image(image)
@@ -18,7 +19,7 @@ def clip(image, text):
         logits_per_image, logits_per_text = model(image, text)
         probs = logits_per_image.softmax(dim=-1).cpu().numpy()
 
-    return probs[0]
+    return probs
 
 demo = gr.Interface(fn=clip, inputs=["text", "image"], outputs="text")
 demo.launch()