PP-OCRv5_mobile_det_pretrained.pdparams 模型训练后导出报错 #16024
GaoMeng-2021
started this conversation in
Documents
Replies: 1 comment
-
需要切换paddlepaddle版本到3.0及以上或者设置Global.export_with_pir=False |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
我使用模型 PP-OCRv5_mobile_det_pretrained.pdparams + PP-OCRv5_server_det.yml,添加自己标注的数据进行训练,其中,PP-OCRv5_server_det.yml 文件仅修改了预训练库位置,标记图片位置等信息,没有修改参数。
环境:
win10 系统,paddlepaddle-gpu v2.5.0, PaddleOCR-release-3.1
使用指令 python tools/train.py -c ./configs/det/PP-OCRv5/PP-OCRv5_server_det.yml 进行训练,没有报错,执行成功。
随后,使用指令 python tools/export_model.py -c "./configs/det/PP-OCRv5/PP-OCRv5_server_det.yml" ^
-o Global.pretrained_model="./output/ch_PP-OCRv5_REC_GM01/latest.pdparams" Global.save_inference_dir="./inference_model/det_v5_gm01.01/"
进行导出,操作失败,提示如下:
[2025/07/11 09:06:53] ppocr WARNING: Skipping import of the encryption module.
W0711 09:06:54.291611 12676 gpu_resources.cc:119] Please NOTE: device: 0, GPU Compute Capability: 8.9, Driver API Version: 12.6, Runtime API Version: 11.2
W0711 09:06:54.301308 12676 gpu_resources.cc:149] device: 0, cuDNN Version: 8.9.
[2025/07/11 09:06:55] ppocr INFO: load pretrain successful from ./output/ch_PP-OCRv5_REC_GM01/latest
[2025/07/11 09:06:55] ppocr INFO: Export inference config file to ./inference_model/det_v5_gm01.01/inference.yml
Skipping import of the encryption module
Traceback (most recent call last):
File "tools/export_model.py", line 37, in
main()
File "tools/export_model.py", line 33, in main
export(config)
File "D:\E\workspace\paddle\GM_Ppocr_01\PaddleOCR-release-3.1\ppocr\utils\export_model.py", line 543, in export
export_single_model(
File "D:\E\workspace\paddle\GM_Ppocr_01\PaddleOCR-release-3.1\ppocr\utils\export_model.py", line 390, in export_single_model
assert (
AssertionError
请教,要如何处理?多谢大佬们指点。
Beta Was this translation helpful? Give feedback.
All reactions