Update app.py

app.py

@@ -2,21 +2,34 @@ import gradio as gr
 # from PIL import Image
 from transformers.utils import logging
 from transformers import BlipForConditionalGeneration, AutoProcessor
+from transformers import pipeline
 
-logging.set_verbosity_error()
+pipe = pipeline("image-to-text",
+                model="./models/Salesforce/blip-image-captioning-base")
 
-model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")
-processor = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
+def launch(input):
+    out = pipe(input)
+    return out[0]['generated_text']
 
-def caption_image(image):
-    inputs = processor(image, return_tensors="pt")
-    out = model.generate(**inputs)
-    caption = processor.decode(out[0], skip_special_tokens=True)
-    return caption
+iface = gr.Interface(launch,
+                     inputs=gr.Image(type='pil'),
+                     outputs="text")
+iface.launch()
 
+# logging.set_verbosity_error()
 
-iface = gr.Interface(fn=caption_image, inputs=["image"], outputs="textbox")
-iface.launch()
+# model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")
+# processor = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
+
+# def caption_image(image):
+#     inputs = processor(image, return_tensors="pt")
+#     out = model.generate(**inputs)
+#     caption = processor.decode(out[0], skip_special_tokens=True)
+#     return caption
+
+
+# iface = gr.Interface(fn=caption_image, inputs=["image"], outputs="textbox")
+# iface.launch()
 # gr.Interface(caption_image, gr.inputs.Image(), "text").launch()
 # gr.Interface(caption_image, image_input, caption_output).launch()