yolo8 actual combat detection face key points

---

---

foreword

Yolo8 can realize human pose estimation, how to migrate to the task of face key point detection? This article is based on yolo8pose to realize the detection of yoloFace Landmark.

One, yolo8 features

The difference between yolo5 and yolo8 is quite big, the biggest difference is the integration of yolo8. It integrates detection, pose and segmentation. And integrate v5, v7 and v8.

2. Use steps

1. Modify the entry of the dataset

The code is as follows (example):

# parent
# ├── ultralytics
# └── datasets
#     └── coco8-pose  ← downloads here (1 MB)

#########################################ori##########################################################################
# # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
# path: ../datasets/coco8-pose  # dataset root dir
# train: images/train  # train images (relative to 'path') 4 images
# val: images/val  # val images (relative to 'path') 4 images
# test:  # test images (optional)
#########################################wqt##########################################################################
# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: 
  /home/wqt/Datasets/300W
  # ../datasets/coco8-pose  # dataset root dir
train: 
  train2yolo.txt
  # images/train  # train images (relative to 'path') 4 images
val: 
  test2yolo.txt
  # images/val  # val images (relative to 'path') 4 images
test:  # test images (optional)

#########################################ori##########################################################################
# # Keypoints
# kpt_shape: [17, 3]  # number of keypoints, number of dims (2 for x,y or 3 for x,y,visible)
# flip_idx: [0, 2, 1, 4, 3, 6, 5, 8, 7, 10, 9, 12, 11, 14, 13, 16, 15]
#########################################wqt##########################################################################