# 深度学习实践

**Repository Path**: jiang-yuhang123/deep-learning-practice

## Basic Information

- **Project Name**: 深度学习实践
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: yolov7-pose
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2024-01-31
- **Last Updated**: 2024-01-31

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# yolov7-pose
Implementation of "YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors"

Pose estimation implimentation is based on [YOLO-Pose](https://arxiv.org/abs/2204.06806). 

在yoloV7-pose基础上添加了任意关键点数量 + 多类别分类代码。

## Training

[yolov7-w6-person.pt](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-w6-person.pt)


``` shell
python train_Ncla_nPoint.py --data data/coco_kpts.yaml --cfg cfg/yolov7-w6-pose.yaml --weights weights/yolov7-w6-person.pt --batch-size 128 --img 640 --device 0 --name yolov7-w6-pose --hyp data/hyp.pose.yaml
```

## Deploy
TensorRT:[https://github.com/nanmi/yolov7-pose](https://github.com/nanmi/yolov7-pose)

## Testing

[yolov7-w6-pose.pt](https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-w6-pose.pt)

``` shell
python test_Ncla.py --data data/coco_kpts.yaml --img 640 --conf 0.5 --iou 0.25 --weights yolov7-w6-pose.pt --kpt-label
```