Upload app.py

app.py

@@ -1,8 +1,8 @@
 import gradio as gr
 from transformers import BlipProcessor, BlipForConditionalGeneration
 from PIL import Image
-from transformers import pipeline
 
+# 加载模型和处理器
 processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
 model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")
 
@@ -12,23 +12,14 @@ def generate_caption(image):
     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):
-    predictions = pipeline(input_img)
-    return input_img, {p["label"]: p["score"] for p in predictions}
-
+# 创建Gradio接口
 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?",
     fn=generate_caption,
-    inputs=gr.inputs.Image(type="pil"),
+    inputs=gr.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__":
-    gradio_app.launch()
+    gradio_app.launch()