paddle的检测模型出v4了，请问可以转换吗

[mrlihellohorld]

[lindadamama]

同问

[lianuo]

同问

[pangmaoran]

同问

[frotms]

@mrlihellohorld @lindadamama @lianuo @pangmaoran 可以

[pangmaoran]

@mrlihellohorld @lindadamama @lianuo @pangmaoran 可以

感谢回复~~刚看了一下，如果用官方ppocrv4转换后是与百度云盘中一样的吗？那现在是不是还不能直接在pytorch上使用，因为我看AnalysisConfig中并不支持v4 rec的框架

[frotms]

@pangmaoran

# ch_PP-OCRv4_det
python ./converter/ch_ppocr_v4_det_converter.py --yaml_path ./configs/det/ch_PP-OCRv4/ch_PP-OCRv4_det_student.yml --src_model_path ch_PP-OCRv4_det_train_dir
# ch_PP-OCRv4_server_det
python ./converter/ch_ppocr_v4_det_server_converter.py --yaml_path ./configs/det/ch_PP-OCRv4/ch_PP-OCRv4_det_teacher.yml --src_model_path ./models_v2.7/ppocrv4/ch_PP-OCRv4_det_server_train_dir

# ch_PP-OCRv4_rec
python ./converter/ch_ppocr_v4_rec_converter.py --yaml_path ./configs/rec/PP-OCRv4/ch_PP-OCRv4_rec.yml --src_model_path ch_PP-OCRv4_rec_train_dir
# ch_PP-OCRv4_server_rec
python ./converter/ch_ppocr_v4_rec_server_converter.py --yaml_path ./configs/rec/PP-OCRv4/ch_PP-OCRv4_rec_hgnet.yml --src_model_path ch_PP-OCRv4_rec_server_train_dir

[pangmaoran]

@pangmaoran

# ch_PP-OCRv4_det
python ./converter/ch_ppocr_v4_det_converter.py --yaml_path ./configs/det/ch_PP-OCRv4/ch_PP-OCRv4_det_student.yml --src_model_path ch_PP-OCRv4_det_train_dir
# ch_PP-OCRv4_server_det
python ./converter/ch_ppocr_v4_det_server_converter.py --yaml_path ./configs/det/ch_PP-OCRv4/ch_PP-OCRv4_det_teacher.yml --src_model_path ./models_v2.7/ppocrv4/ch_PP-OCRv4_det_server_train_dir

# ch_PP-OCRv4_rec
python ./converter/ch_ppocr_v4_rec_converter.py --yaml_path ./configs/rec/PP-OCRv4/ch_PP-OCRv4_rec.yml --src_model_path ch_PP-OCRv4_rec_train_dir
# ch_PP-OCRv4_server_rec
python ./converter/ch_ppocr_v4_rec_server_converter.py --yaml_path ./configs/rec/PP-OCRv4/ch_PP-OCRv4_rec_hgnet.yml --src_model_path ch_PP-OCRv4_rec_server_train_dir

感谢大佬 刚没仔细读关于推理那块的doc 我悟了！✨✨✨