X-AnyLabeling使用教程

X-AnyLabeling下载链接：
https://github.com/CVHub520/X-AnyLabeling/releases/tag/v2.3.6
模型下载地址：
https://github.com/CVHub520/X-AnyLabeling/releases/
加载自定义模型文档：
https://github.com/CVHub520/X-AnyLabeling/blob/main/docs/zh_cn/custom_model.md

1.AI 模型自动分割标注使用教程
2.AI 模型自动目标检测标注使用教程

3.加载自定义模型


4.常见模型config.yaml设置
（1）edge sam config.yaml

type: edge_sam
name: edge_sam-r20231213
display_name: EdgeSAM
encoder_model_path: edge_sam_encoder.onnx
decoder_model_path: edge_sam_decoder.onnx

（2）yolov8-pose config.yaml

type: yolov8_pose
name: yolov8n-pose-r20231103
display_name: YOLOv8n-Pose Ultralytics
model_path: yolov8n-pose.onnx
confidence_threshold: 0.5
nms_threshold: 0.6
show_boxes: True
classes:
  - person
keypoints:
  - nose
  - left_eye
  - right_eye
  - left_ear
  - right_ear
  - left_shoulder
  - right_shoulder
  - left_elbow
  - right_elbow
  - left_wrist
  - right_wrist
  - left_hip
  - right_hip
  - left_knee
  - right_knee
  - left_ankle
  - right_ankle

（3）yolov10l config.yaml

classes:
- person
- bicycle
- car
- motorcycle
- airplane
- bus
- train
- truck
- boat
- traffic light
- fire hydrant
- stop sign
- parking meter
- bench
- bird
- cat
- dog
- horse
- sheep
- cow
- elephant
- bear
- zebra
- giraffe
- backpack
- umbrella
- handbag
- tie
- suitcase
- frisbee
- skis
- snowboard
- sports ball
- kite
- baseball bat
- baseball glove
- skateboard
- surfboard
- tennis racket
- bottle
- wine glass
- cup
- fork
- knife
- spoon
- bowl
- banana
- apple
- sandwich
- orange
- broccoli
- carrot
- hot dog
- pizza
- donut
- cake
- chair
- couch
- potted plant
- bed
- dining table
- toilet
- tv
- laptop
- mouse
- remote
- keyboard
- cell phone
- microwave
- oven
- toaster
- sink
- refrigerator
- book
- clock
- vase
- scissors
- teddy bear
- hair drier
- toothbrush
confidence_threshold: 0.45
display_name: YOLOv10l Ultralytics
has_downloaded: true
input_height: 640
input_width: 640
model_path: yolov10l.onnx
name: yolov10l-r20240525
nms_threshold: 0.45
score_threshold: 0.5
type: yolov10

注：classes不能缺失或替换顺序，否则即使加载模型成功，label不正确

5.一次运行所有图片

6.已经标注文件导入标注信息
导入后，覆盖标注信息

7. json文件更换为其它格式文件，如VOC .xml