Update app.py

app.py

@@ -9,11 +9,27 @@ from transformers import BlipProcessor, BlipForConditionalGeneration
 model = BlipForConditionalGeneration.from_pretrained('jaimin/Imagecap')
 processor = BlipProcessor.from_pretrained('jaimin/Imagecap')
 
-def launch(input):
-    image = Image.open(requests.get(input, stream=True).raw).convert('RGB')
-    inputs = processor(image, return_tensors="pt")
-    out = model.generate(**inputs)
-    return processor.decode(out[0], skip_special_tokens=True)
-
-iface = gr.Interface(launch, inputs="text", outputs="text")
-iface.launch()
+
+
+def predict(image,max_length=64, num_beams=4):
+  image = image.convert('RGB')
+  image = feature_extractor(image, return_tensors="pt").pixel_values.to(device)
+  #clean_text = lambda x: x.replace('<|endoftext|>','').split('\n')[0]
+  caption_ids = model.generate(image, max_length = max_length)[0]
+  caption_text = tokenizer.decode(caption_ids)
+  return processor.decode(caption_ids[0], skip_special_tokens=True)
+
+
+
+input = gr.inputs.Image(label="Upload your Image", type = 'pil', optional=True)
+output = gr.outputs.Textbox(label="Captions")
+
+title = "ImageCap"
+
+interface = gr.Interface(
+        fn=predict,
+        inputs = input,
+        outputs=output,
+        title=title,
+    )
+interface.launch(debug=True)