Qwen2-VL微调体验

发布于：2024-12-19 ⋅ 阅读:(17) ⋅ 点赞:(0)
微信交流群：https://732903.hlcode.cn/?id=NK1fWUR

1.配置环境

2.数据集准备

3.模型下载

4.注册SwanLab

5.微调

6.训练过程可视化

1.配置环境

本博客使用的是2B模型，所以仅用了单卡3090，若大一点的模型，自行根据实际情况准备显卡

安装Python>=3.8

安装Qwen2-VL必要的库

pip install modelscope==1.18.0

pip install transformers==4.46.2

pip install accelerate==1.1.1

pip install datasets==2.18.0

pip install peft==0.13.2

pip install qwen-vl-utils==0.0.8

2.数据集准备

本博客使用的是coco_2014_caption数据集中的部分，json格式如下：

数据集下载可以使用如下同样会产生一个csv：


from modelscope.msdatasets import MsDataset
import os
import pandas as pd

MAX_DATA_NUMBER = 500


if not os.path.exists('coco_2014_caption'):
    # 从modelscope下载COCO 2014图像描述数据集
    ds =  MsDataset.load('modelscope/coco_2014_caption', subset_name='coco_2014_caption', split='train')
    print(len(ds))
    
    total = min(MAX_DATA_NUMBER, len(ds))

    
    os.makedirs('coco_2014_caption', exist_ok=True)

    
    image_paths = []
    captions = []

    for i in range(total):
        # 获取每个样本的信息
        item = ds[i]
        image_id = item['image_id']
        caption = item['caption']
        image = item['image']
        
        # 保存图片并记录路径
        image_path = os.path.abspath(f'coco_2014_caption/{image_id}.jpg')
        image.save(image_path)
        
        # 将路径和描述添加到列表中
        image_paths.append(image_path)
        captions.append(caption)
        
        # 每处理50张图片打印一次进度
        if (i + 1) % 50 == 0:
            print(f'Processing {i+1}/{total} images ({(i+1)/total*100:.1f}%)')

    # 将图片路径和描述保存为CSV文件
    df = pd.DataFrame({
        'image_path': image_paths,
        'caption': captions
    })
    
    # 将数据保存为CSV文件
    df.to_csv('./coco-2024-dataset.csv', index=False)
    
    print(f'数据处理完成，共处理了{total}张图片')

else:
    print('coco_2014_caption目录已存在,跳过数据处理步骤')

我们需要得到json，所以执行下面脚本得到：

import pandas as pd
import json

# 载入CSV文件
df = pd.read_csv('./coco-2024-dataset.csv')
conversations = []

# 添加对话数据
for i in range(len(df)):
    conversations.append({
        "id": f"identity_{i+1}",
        "conversations": [
            {
                "from": "user",
                "value": f"COCO Yes: <|vision_start|>{df.iloc[i]['image_path']}<|vision_end|>"
            },
            {
                "from": "assistant", 
                "value": df.iloc[i]['caption']
            }
        ]
    })

# 保存为Json
with open('data_vl.json', 'w', encoding='utf-8') as f:
    json.dump(conversations, f, ensure_ascii=False, indent=2)

以上则是数据集准备，若使用自定义数据集则根据上面的格式准备！！！

3.模型下载

本博客使用魔塔社区中的Qwen2-VL-2B模型

from modelscope import snapshot_download, AutoTokenizer
from transformers import TrainingArguments, Trainer, DataCollatorForSeq2Seq, Qwen2VLForConditionalGeneration, AutoProcessor
import torch

model_dir = snapshot_download("Qwen/Qwen2-VL-2B-Instruct", cache_dir="./", revision="master")
tokenizer = AutoTokenizer.from_pretrained("./Qwen/Qwen2-VL-2B-Instruct/", use_fast=False, trust_remote_code=True)
model = Qwen2VLForConditionalGeneration.from_pretrained("./Qwen/Qwen2-VL-2B-Instruct/", device_map="auto", torch_dtype=torch.bfloat16, trust_remote_code=True,)
model.enable_input_require_grads()

4.注册SwanLab

为了微调时随时查看各项指标，注册SwanLab,复制key,粘贴到运行过程中，如下图：

5.微调

微调前保证当前文件夹下面包含以下：

train.py代码如下：

import torch
from datasets import Dataset
from modelscope import snapshot_download, AutoTokenizer
from swanlab.integration.transformers import SwanLabCallback
from qwen_vl_utils import process_vision_info
from peft import LoraConfig, TaskType, get_peft_model, PeftModel
from transformers import (
    TrainingArguments,
    Trainer,
    DataCollatorForSeq2Seq,
    Qwen2VLForConditionalGeneration,
    AutoProcessor,
)
import swanlab
import json


def process_func(example):
    """
    将数据集进行预处理
    """
    MAX_LENGTH = 8192
    input_ids, attention_mask, labels = [], [], []
    conversation = example["conversations"]
    input_content = conversation[0]["value"]
    output_content = conversation[1]["value"]
    file_path = input_content.split("<|vision_start|>")[1].split("<|vision_end|>")[0]  # 获取图像路径
    messages = [
        {
            "role": "user",
            "content": [
                {
                    "type": "image",
                    "image": f"{file_path}",
                    "resized_height": 280,
                    "resized_width": 280,
                },
                {"type": "text", "text": "COCO Yes:"},
            ],
        }
    ]
    text = processor.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )  # 获取文本
    image_inputs, video_inputs = process_vision_info(messages)  # 获取数据数据（预处理过）
    inputs = processor(
        text=[text],
        images=image_inputs,
        videos=video_inputs,
        padding=True,
        return_tensors="pt",
    )
    inputs = {key: value.tolist() for key, value in inputs.items()} #tensor -> list,为了方便拼接
    instruction = inputs

    response = tokenizer(f"{output_content}", add_special_tokens=False)


    input_ids = (
            instruction["input_ids"][0] + response["input_ids"] + [tokenizer.pad_token_id]
    )

    attention_mask = instruction["attention_mask"][0] + response["attention_mask"] + [1]
    labels = (
            [-100] * len(instruction["input_ids"][0])
            + response["input_ids"]
            + [tokenizer.pad_token_id]
    )
    if len(input_ids) > MAX_LENGTH:  # 做一个截断
        input_ids = input_ids[:MAX_LENGTH]
        attention_mask = attention_mask[:MAX_LENGTH]
        labels = labels[:MAX_LENGTH]

    input_ids = torch.tensor(input_ids)
    attention_mask = torch.tensor(attention_mask)
    labels = torch.tensor(labels)
    inputs['pixel_values'] = torch.tensor(inputs['pixel_values'])
    inputs['image_grid_thw'] = torch.tensor(inputs['image_grid_thw']).squeeze(0)  #由（1,h,w)变换为（h,w）
    return {"input_ids": input_ids, "attention_mask": attention_mask, "labels": labels,
            "pixel_values": inputs['pixel_values'], "image_grid_thw": inputs['image_grid_thw']}


def predict(messages, model):
    # 准备推理
    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("cuda")

    # 生成输出
    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]


# 在modelscope上下载Qwen2-VL模型到本地目录下
model_dir = snapshot_download("Qwen/Qwen2-VL-2B-Instruct", cache_dir="./", revision="master")

# 使用Transformers加载模型权重
tokenizer = AutoTokenizer.from_pretrained("./Qwen/Qwen2-VL-2B-Instruct/", use_fast=False, trust_remote_code=True)
processor = AutoProcessor.from_pretrained("./Qwen/Qwen2-VL-2B-Instruct")

model = Qwen2VLForConditionalGeneration.from_pretrained("./Qwen/Qwen2-VL-2B-Instruct/", device_map="auto", torch_dtype=torch.bfloat16, trust_remote_code=True,)
model.enable_input_require_grads()  # 开启梯度检查点时，要执行该方法

# 处理数据集：读取json文件
# 拆分成训练集和测试集，保存为data_vl_train.json和data_vl_test.json
train_json_path = "data_vl.json"
with open(train_json_path, 'r') as f:
    data = json.load(f)
    train_data = data[:-4]
    test_data = data[-4:]

with open("data_vl_train.json", "w") as f:
    json.dump(train_data, f)

with open("data_vl_test.json", "w") as f:
    json.dump(test_data, f)

train_ds = Dataset.from_json("data_vl_train.json")
train_dataset = train_ds.map(process_func)

# 配置LoRA
config = LoraConfig(
    task_type=TaskType.CAUSAL_LM,
    target_modules=["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"],
    inference_mode=False,  # 训练模式
    r=64,  # Lora 秩
    lora_alpha=16,  # Lora alaph，具体作用参见 Lora 原理
    lora_dropout=0.05,  # Dropout 比例
    bias="none",
)

# 获取LoRA模型
peft_model = get_peft_model(model, config)

# 配置训练参数
args = TrainingArguments(
    output_dir="./output/Qwen2-VL-2B",
    per_device_train_batch_size=4,
    gradient_accumulation_steps=4,
    logging_steps=10,
    logging_first_step=5,
    num_train_epochs=2,
    save_steps=100,
    learning_rate=1e-4,
    save_on_each_node=True,
    gradient_checkpointing=True,
    report_to="none",
)
        
# 设置SwanLab回调
swanlab_callback = SwanLabCallback(
    project="Qwen2-VL-finetune",
    experiment_name="qwen2-vl-coco2014",
    config={
        "model": "https://modelscope.cn/models/Qwen/Qwen2-VL-2B-Instruct",
        "dataset": "https://modelscope.cn/datasets/modelscope/coco_2014_caption/quickstart",
        "github": "https://github.com/datawhalechina/self-llm",
        "prompt": "COCO Yes: ",
        "train_data_number": len(train_data),
        "lora_rank": 64,
        "lora_alpha": 16,
        "lora_dropout": 0.1,
    },
)

# 配置Trainer
trainer = Trainer(
    model=peft_model,
    args=args,
    train_dataset=train_dataset,
    data_collator=DataCollatorForSeq2Seq(tokenizer=tokenizer, padding=True),
    callbacks=[swanlab_callback],
)

# 开启模型训练
trainer.train()

# 配置测试参数
val_config = LoraConfig(
    task_type=TaskType.CAUSAL_LM,
    target_modules=["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"],
    inference_mode=True,  # 训练模式
    r=64,  # Lora 秩
    lora_alpha=16,  # Lora alaph，具体作用参见 Lora 原理
    lora_dropout=0.05,  # Dropout 比例
    bias="none",
)

# 获取测试模型
val_peft_model = PeftModel.from_pretrained(model, model_id="./output/Qwen2-VL-2B/checkpoint-62", config=val_config)

# 读取测试数据
with open("data_vl_test.json", "r") as f:
    test_dataset = json.load(f)

test_image_list = []
for item in test_dataset:
    input_image_prompt = item["conversations"][0]["value"]
    # 去掉前后的<|vision_start|>和<|vision_end|>
    origin_image_path = input_image_prompt.split("<|vision_start|>")[1].split("<|vision_end|>")[0]
    
    messages = [{
        "role": "user", 
        "content": [
            {
            "type": "image", 
            "image": origin_image_path
            },
            {
            "type": "text",
            "text": "COCO Yes:"
            }
        ]}]
    
    response = predict(messages, val_peft_model)
    messages.append({"role": "assistant", "content": f"{response}"})
    print(messages[-1])

    test_image_list.append(swanlab.Image(origin_image_path, caption=response))

swanlab.log({"Prediction": test_image_list})

swanlab.finish()

6.训练过程可视化

网站公告

今日签到

点亮在社区的每一天
去签到

热门文章

最新发布