import torch
from modelscope import snapshot_download
from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor
from qwen_vl_utils import process_vision_info
# 修改默认缓存路径
import os
import numpy

print('torch版本:',torch.__version__)
print('numpy版本:',numpy.__version__)
print(f"当前设备: {torch.cuda.get_device_name(0) if torch.cuda.is_available() else 'CPU'}")


os.environ['MODELSCOPE_CACHE'] = 'D:\dev-venv\modelscope'
# model_dir = snapshot_download('Qwen/Qwen2.5-VL-7B-Instruct')
model_dir = snapshot_download('Qwen/Qwen2.5-VL-7B-Instruct')

# default: Load the model on the available device(s)
model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
    model_dir, torch_dtype=torch.bfloat16, device_map="auto"
)

processor = AutoProcessor.from_pretrained(model_dir,max_pixels=1028*28*28)

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "image",
                "image": "C:/Users/33506/Desktop/1740100328531.jpg",
                "description": "这是一个拍摄水库溢洪道口的图片",
            },
            {"type": "text",
             "text": "判断画面中是否存在钓鱼或游泳的人员存在"},
        ],
    }
]

# Preparation for inference
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)

# Inference: Generation of the output
generated_ids = model.generate(**inputs, max_new_tokens=1000)
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
)
print(output_text)