import torch
from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info
import gradio as gr

# 加载模型和处理器
try:
    model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
        "Qwen/Qwen2.5-VL-7B-Instruct", 
        torch_dtype="auto", 
        device_map="auto"
    )
    processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct")
except Exception as e:
    print(f"模型加载失败: {e}")

# 定义处理函数
def recognize_and_analyze(image, text_prompt):
    try:
        messages = [
            {
                "role": "user",
                "content": [
                    {"type": "image", "image": image},
                    {"type": "text", "text": text_prompt},
                ],
            }
        ]

        # 准备推理输入数据
        text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
        image_inputs, video_inputs = process_vision_info(messages)
        inputs = processor(
            text=[text],
            images=image_inputs,
            videos=video_inputs,
            padding=True,
            return_tensors="pt",
        )
        inputs = inputs.to(model.device)

        # 推理：生成输出文本
        generated_ids = model.generate(**inputs, max_new_tokens=128)
        generated_ids_trimmed = [
            out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
        ]
        output_text = processor.batch_decode(
            generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
        )
        
        return output_text[0]
    except Exception as e:
        return f"处理过程中出现错误: {e}"

# 设置 Gradio 界面
interface = gr.Interface(
    fn=recognize_and_analyze,
    inputs=[
        gr.Image(type="filepath", label="上传图像"),
        gr.Textbox(label="输入描述文本"),
    ],
    outputs=gr.Textbox(label="识别结果"),
    title="Qwen2.5-VL 物体识别与分析",
    description="上传图像并输入描述文本以获取识别和分析结果。",
)

# 启动 Gradio 应用
if __name__ == "__main__":
    interface.launch()