# TTMeterReader

**Repository Path**: aiquanton/meter-reader

## Basic Information

- **Project Name**: TTMeterReader
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-09-05
- **Last Updated**: 2025-09-05

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# 项目介绍


# 数据集

1. labelme 标注100个数据
2. 切换 指针 -》 关键点
3. 数据集划分 80%训练 20%测试
4. 转换为yolo格式


# 模型训练

## CUDA 安装
https://developer.nvidia.com/cuda-toolkit-archive

## 安装pytorch for GPU
https://pytorch.org/get-started/previous-versions/
conda install pytorch==1.13.1 torchvision==0.14.1 torchaudio==0.13.1 cudatoolkit=11.6 -c pytorch -c conda-forge
pip install numpy==1.22.4


0. conda create --name yolov8 python=3.9
conda activate yolov8
1. pip install ultralytics --upgrade -i https://pypi.tuna.tsinghua.edu.cn/simple
2. pip install numpy opencv-python pillow pandas matplotlib seaborn tqdm wandb seedir emoji -i https://pypi.tuna.tsinghua.edu.cn/simple

开启旋转增强
3. yolo pose train data=coco8-pose.yaml  model=yolov8n-pose.pt project=JNMeterReader name=time0 epochs=600  imgsz=960 fliplr=0.0  flipud=0.0 degrees=30 shear=20  lr0=0.001 pose=15.0

关闭旋转增强
4. yolo pose train data=coco8-pose.yaml  model=yolov8n-pose.pt project=JNMeterReader name=time0 epochs=400 batch=60 fliplr=0.0  flipud=0.0



3. wandb login 过程观察


5. 预测
yolo detect predict model=D:\aiquantong\JNMeterReader.git\JNMeterReader\JNMeterReader\time0\weights\best.pt  source=D:\aiquantong\JNMeterReader.git\JNMeterReader\datasets\detect_test save=True conf=0.5


# 代码
```
    https://gitee.com/aiquanton/JNMeterReader.git
```






# 运行



# 结果



# 参考



# 贡献