Upload app.py

app.py

@@ -1,6 +1,17 @@
 import gradio as gr
+from transformers import BlipProcessor, BlipForConditionalGeneration
+from PIL import Image
 from transformers import pipeline
 
+processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
+model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")
+
+def generate_caption(image):
+    inputs = processor(image, return_tensors="pt")
+    outputs = model.generate(**inputs)
+    description = processor.decode(outputs[0], skip_special_tokens=True)
+    return description
+
 pipeline = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog")
 
 def predict(input_img):
@@ -8,10 +19,15 @@ def predict(input_img):
     return input_img, {p["label"]: p["score"] for p in predictions}
 
 gradio_app = gr.Interface(
-    predict,
-    inputs=gr.Image(label="Select hot dog candidate", sources=['upload', 'webcam'], type="pil"),
-    outputs=[gr.Image(label="Processed Image"), gr.Label(label="Result", num_top_classes=2)],
-    title="Hot Dog? Or Not?",
+    # predict,
+    # inputs=gr.Image(label="Select hot dog candidate", sources=['upload', 'webcam'], type="pil"),
+    # outputs=[gr.Image(label="Processed Image"), gr.Label(label="Result", num_top_classes=2)],
+    # title="Hot Dog? Or Not?",
+    fn=generate_caption,
+    inputs=gr.inputs.Image(type="pil"),
+    outputs="text",
+    title="图片描述生成器",
+    description="上传一张图片，生成相应的描述。"
 )
 
 if __name__ == "__main__":