PaddleOCR试用官方模型(三)

det检测:

(base) C:\Users\20010819>activate paddle38

(paddle38) C:\Users\20010819>d:

(paddle38) D:\>cd D:/ML/Project0/PaddleOCR-release-2.5/

(paddle38) D:\ML\Project0\PaddleOCR-release-2.5>python tools/train.py -c configs/det/det_mv3_db.yml

det导出:

(base) C:\Users\20010819>activate paddle38

(paddle38) C:\Users\20010819>d:

(paddle38) D:\>cd D:/ML/Project0/PaddleOCR-release-2.5/

(paddle38) D:\ML\Project0\PaddleOCR-release-2.5>python tools/export_model.py -c configs/det/det_mv3_db.yml -o Global.pretrained_model=./output/db_mv3/best_accuracy Global.save_inference_dir=./inference/db_mv3

det评估:

(base) C:\Users\20010819>activate paddle38

(paddle38) C:\Users\20010819>d:

(paddle38) D:\>cd D:/ML/Project0/PaddleOCR-release-2.5/

(paddle38) D:\ML\Project0\PaddleOCR-release-2.5>python tools/eval.py -c configs/det/det_mv3_db.yml -o Global.pretrained_model="output/det_db/best_accuracy"

rec训练:

(base) C:\Users\20010819>activate paddle38

(paddle38) C:\Users\20010819>d:

(paddle38) D:\>cd D:/ML/Project0/PaddleOCR-release-2.5/

(paddle38) D:\ML\Project0\PaddleOCR-release-2.5>python tools/train.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml

rec导出:

(base) C:\Users\20010819>activate paddle38

(paddle38) C:\Users\20010819>d:

(paddle38) D:\>cd D:/ML/Project0/PaddleOCR-release-2.5/

(paddle38) D:\ML\Project0\PaddleOCR-release-2.5>python tools/export_model.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml -o Global.checkpoints=./output/rec_chinese_lite_v2.0/latest Global.save_inference_dir=./inference/rec_chinese_lite_v2.0/

rec评估;

(base) C:\Users\20010819>activate paddle38

(paddle38) C:\Users\20010819>d:

(paddle38) D:\>cd D:/ML/Project0/PaddleOCR-release-2.5/

(paddle38) D:\ML\Project0\PaddleOCR-release-2.5>python tools/eval.py -c configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml -o Global.checkpoints=./output/rec_chinese_lite_v2.0/latest 

你可能感兴趣的:(python,开发语言,paddlepaddle,paddle)