license: mit pipeline_tag: image-text-to-text library_name: transformers base_model:

• OpenGVLab/InternVL2-1B base_model_relation: merge language:
• multilingual tags:
• internvl
• custom_code

Mini-InternVL2-DA-RS

[ 📂 GitHub ] [ 🆕 Blog ] [ 📜 Mini-InternVL ] [ 📜 InternVL 1.0 ] [ 📜 InternVL 1.5 ] [ 📜 InternVL 2.5 ]

[ 🗨️ InternVL Chat Demo ] [ 🤗 HF Demo ] [ 🚀 Quick Start ] [ 📖 中文解读 ] [ 📖 Documents ]

简介

我们发布了针对特定领域的适配模型：自动驾驶、医学影像和遥感图像。

这些模型基于Mini-InternVL，通过统一的适配框架进行微调，在特定领域任务上取得了良好的性能。

评估脚本详见文档。

训练数据集

• 通用领域数据集：

  ShareGPT4V、AllSeeingV2、LLaVA-Instruct-ZH、DVQA、ChartQA、AI2D、DocVQA、GeoQA+、SynthDoG-EN

• 自动驾驶数据集：

  DriveLM。

快速开始

我们提供使用transformers运行Mini-InternVL2-1B的示例代码。

请使用transformers>=4.37.2以确保模型正常运行。

import numpy as np
import torch
import torchvision.transforms as T
from decord import VideoReader, cpu
from PIL import Image
from torchvision.transforms.functional import InterpolationMode
from transformers import AutoModel, AutoTokenizer

IMAGENET_MEAN = (0.485, 0.456, 0.406)
IMAGENET_STD = (0.229, 0.224, 0.225)

def build_transform(input_size):
    MEAN, STD = IMAGENET_MEAN, IMAGENET_STD
    transform = T.Compose([
        T.Lambda(lambda img: img.convert('RGB') if img.mode != 'RGB' else img),
        T.Resize((input_size, input_size), interpolation=InterpolationMode.BICUBIC),
        T.ToTensor(),
        T.Normalize(mean=MEAN, std=STD)
    ])
    return transform

def find_closest_aspect_ratio(aspect_ratio, target_ratios, width, height, image_size):
    best_ratio_diff = float('inf')
    best_ratio = (1, 1)
    area = width * height
    for ratio in target_ratios:
        target_aspect_ratio = ratio[0] / ratio[1]
        ratio_diff = abs(aspect_ratio - target_aspect_ratio)
        if ratio_diff < best_ratio_diff:
            best_ratio_diff = ratio_diff
            best_ratio = ratio
        elif ratio_diff == best_ratio_diff:
            if area > 0.5 * image_size * image_size * ratio[0] * ratio[1]:
                best_ratio = ratio
    return best_ratio

def dynamic_preprocess(image, min_num=1, max_num=12, image_size=448, use_thumbnail=False):
    orig_width, orig_height = image.size
    aspect_ratio = orig_width / orig_height

    # 计算现有图像的宽高比
    target_ratios = set(
        (i, j) for n in range(min_num, max_num + 1) for i in range(1, n + 1) for j in range(1, n + 1) if
        i * j <= max_num and i * j >= min_num)
    target_ratios = sorted(target_ratios, key=lambda x: x[0] * x[1])

    # 找到最接近目标宽高比的比率
    target_aspect_ratio = find_closest_aspect_ratio(
        aspect_ratio, target_ratios, orig_width, orig_height, image_size)

    # 计算目标宽度和高度
    target_width = image_size * target_aspect_ratio[0]
    target_height = image_size * target_aspect_ratio[1]
    blocks = target_aspect_ratio[0] * target_aspect_ratio[1]

    # 调整图像大小
    resized_img = image.resize((target_width, target_height))
    processed_images = []
    for i in range(blocks):
        box = (
            (i % (target_width // image_size)) * image_size,
            (i // (target_width // image_size)) * image_size,
            ((i % (target_width // image_size)) + 1) * image_size,
            ((i // (target_width // image_size)) + 1) * image_size
        )
        # 分割图像
        split_img = resized_img.crop(box)
        processed_images.append(split_img)
    assert len(processed_images) == blocks
    if use_thumbnail and len(processed_images) != 1:
        thumbnail_img = image.resize((image_size, image_size))
        processed_images.append(thumbnail_img)
    return processed_images

def load_image(image_file, input_size=448, max_num=12):
    image = Image.open(image_file).convert('RGB')
    transform = build_transform(input_size=input_size)
    images = dynamic_preprocess(image, image_size=input_size, use_thumbnail=True, max_num=max_num)
    pixel_values = [transform(image) for image in images]
    pixel_values = torch.stack(pixel_values)
    return pixel_values

# 如需使用多GPU加载模型，请参考`Multiple GPUs`部分
path = 'OpenGVLab/Mini-InternVL2-1B-DA-Drivelm'
model = AutoModel.from_pretrained(
    path,
    torch_dtype=torch.bfloat16,
    low_cpu_mem_usage=True,
    use_flash_attn=True,
    trust_remote_code=True).eval().cuda()
tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)

# 在`max_num`中设置最大分块数
pixel_values = load_image('path/to/image.jpg', max_num=12).to(torch.bfloat16).cuda()
generation_config = dict(max_new_tokens=1024, do_sample=True)

# 纯文本对话
question = '你好，你是谁？'
response, history = model.chat(tokenizer, None, question, generation_config, history=None, return_history=True)
print(f'用户: {question}\n助手: {response}')

question = '能给我讲个故事吗？'
response, history = model.chat(tokenizer, None, question, generation_config, history=history, return_history=True)
print(f'用户: {question}\n助手: {response}')

# 单图单轮对话
question = '<image>\n请简要描述这张图片。'
response = model.chat(tokenizer, pixel_values, question, generation_config)
print(f'用户: {question}\n助手: {response}')

# 单图多轮对话
question = '<image>\n请详细描述这张图片。'
response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=None, return_history=True)
print(f'用户: {question}\n助手: {response}')

question = '请根据图片写一首诗。'
response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=history, return_history=True)
print(f'用户: {question}\n助手: {response}')

# 多图多轮对话，拼接图像
pixel_values1 = load_image('path/to/image1.jpg', max_num=12).to(torch.bfloat16).cuda()
pixel_values2 = load_image('path/to/image2.jpg', max_num=12).to(torch.bfloat16).cuda()
pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0)

question = '<image>\n详细描述这两张图片。'
response, history = model.chat(tokenizer, pixel_values, question, generation_config,
                               history=None, return_history=True)
print(f'用户: {question}\n助手: {response}')

question = '这两张图片有什么相似和不同之处。'
response, history = model.chat(tokenizer, pixel_values, question, generation_config,
                               history=history, return_history=True)
print(f'用户: {question}\n助手: {response}')

# 多图多轮对话，独立图像
pixel_values1 = load_image('path/to/image1.jpg', max_num=12).to(torch.bfloat16).cuda()
pixel_values2 = load_image('path/to/image2.jpg', max_num=12).to(torch.bfloat16).cuda()
pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0)
num_patches_list = [pixel_values1.size(0), pixel_values2.size(0)]

question = 'Image-1: <image>\nImage-2: <image>\n详细描述这两张图片。'
response, history = model.chat(tokenizer, pixel_values, question, generation_config,
                               num_patches_list=num_patches_list,
                               history=None, return_history=True)
print(f'用户: {question}\n助手: {response}')

question = '这两张图片有什么相似和不同之处。'
response, history = model.chat(tokenizer, pixel_values, question, generation_config,
                               num_patches_list=num_patches_list,
                               history=history, return_history=True)
print(f'用户: {question}\n助手: {response}')

# 批处理推理，每个样本单图
pixel_values1 = load_image('path/to/image1.jpg', max_num=12).to(torch.bfloat16).cuda()
pixel_values2 = load_image('path/to/image1.jpg', max_num=12).to(torch.bfloat16).cuda()
num_patches_list = [pixel_values1.size(0), pixel_values2.size(0)]
pixel_values = torch.cat((pixel_values1, pixel_values2), dim=0)

questions = ['<image>\n详细描述这张图片。'] * len(num_patches_list)
responses = model.batch_chat(tokenizer, pixel_values,
                             num_patches_list=num_patches_list,
                             questions=questions,
                             generation_config=generation_config)
for question, response in zip(questions, responses):
    print(f'用户: {question}\n助手: {response}')

引用

如果您在研究中发现本项目有用，请考虑引用：

@article{gao2024mini,
  title={Mini-internvl: A flexible-transfer pocket multimodal model with 5\% parameters and 90\% performance},
  author={Gao, Zhangwei and Chen, Zhe and Cui, Erfei and Ren, Yiming and Wang, Weiyun and Zhu, Jinguo and Tian, Hao and Ye, Shenglong and He, Junjun and Zhu, Xizhou and others},
  journal={arXiv preprint arXiv:2410.16261},
  year={2024}
}
@article{chen2024expanding,
  title={Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling},
  author={Chen, Zhe and Wang, Weiyun and Cao, Yue and Liu, Yangzhou and Gao, Zhangwei and Cui, Erfei and Zhu, Jinguo and Ye, Shenglong and Tian, Hao and Liu, Zhaoyang and others},
  journal={arXiv preprint arXiv:2412.05271},
  year={2024}
}
@article{chen2024far,
  title={How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites},
  author={Chen, Zhe and Wang, Weiyun and Tian, Hao and Ye, Shenglong and Gao, Zhangwei and Cui, Erfei and Tong, Wenwen and Hu, Kongzhi and Luo, Jiapeng and Ma, Zheng and others},
  journal={arXiv preprint arXiv:2404.16821},
  year={2024}
}
@inproceedings{chen2024internvl,
  title={Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks},
  author={Chen, Zhe and Wu, Jiannan and Wang, Wenhai and Su, Weijie and Chen, Guo and Xing, Sen and Zhong, Muyan and Zhang, Qinglong and Zhu, Xizhou and Lu, Lewei and others},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  pages={24185--24198},
  year={2024}
}