25 lines
1.4 KiB
Plaintext
25 lines
1.4 KiB
Plaintext
使用cmd做
|
||
|
||
創建一個可以跑yolov5的envs
|
||
從roboflow下載yolov8格式的資料集放到golfaceyolov5，範例如test1data。
|
||
修改test1data裡面的data.yaml，可直接照格式複製，記得改路徑。
|
||
|
||
要train的時候記得cd到yolov5裡面
|
||
train的指令:
|
||
python train.py --data C:/Users/rd_de/yolov5git/data/10-02+10-01+10-038class/data.yaml --weights for720best.pt --img 640 --batch-size 8 --epochs 300 --device 0
|
||
|
||
train完到runs/train/expX看結果，裡面有weight
|
||
|
||
測試test data
|
||
python detect.py --weights runs/train/exp27/weights/best.pt --source test14data/test/images --img 640 --conf 0.25 --device 0
|
||
|
||
docker run --rm -it -v $(wslpath -u 'C:\Users\rd_de\golfaceyolov5\yolov5'):/workspace/yolov5 kneron/toolchain:latest
|
||
|
||
轉onnx
|
||
(yolov5_export) C:\Users\rd_de\yolov5git\yolov5>python exporting/yolov5_export.py --data data/mepretrained_paths_720.yaml
|
||
|
||
(yolov5_export) C:\Users\rd_de\yolov5git\ai_training\detection\yolov5>python -m onnxsim C:/Users/rd_de/yolov5git/runs/train/exp29735/weights/best.onnx C:/Users/rd_de/yolov5git/runs/train/exp29735/weights/best_simplified.onnx
|
||
|
||
root@DESKTOP-R99GP8R:~# docker run --rm -it -v $(wslpath -u 'C:\Users\rd_de\golfaceyolov5\yolov5'):/workspace/yolov5 kneron/toolchain:latest
|
||
|
||
docker cp 2f8a95bb8bd9:/data1/kneron_flow/runs/train/exp6/weights/models_630.nef C:\Users\rd_de\golfaceyolov5\yolov5\runs\train\exp6\weights |