转Inference模型时发生错误:TypeError: can only concatenate list (not "NoneType") to list #13111
Unanswered
chunmengtu
asked this question in
Q&A
Replies: 1 comment 3 replies
-
v3版本的模型用paddleocr2.6.0版本的可以转换成功。 |
Beta Was this translation helpful? Give feedback.
3 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
转换指令为:python tools/export_model.py -c inference/ch_PP-OCR_v3_rec/config.yml -o Global.pretrained_model=./inference/ch_PP-OCR_v3_rec/best_accuracy Global.save_inference_dir=./inferences_rec/
模型为官方“基于PP-OCRv3的液晶屏读数识别”模型:https://github.com/PaddlePaddle/PaddleOCR/blob/main/applications/%E6%B6%B2%E6%99%B6%E5%B1%8F%E8%AF%BB%E6%95%B0%E8%AF%86%E5%88%AB.md
报错内容为:
shape=[None] + input_shape, dtype="float32"),
TypeError: can only concatenate list (not "NoneType") to list
环境为:
torch 2.2.0+cu118
torchaudio 2.2.0+cu118
torchvision 0.17.0+cu118
paddleocr 2.7.3
paddlepaddle-gpu 2.6.1
numpy 1.23.5
只有识别模型无法转换,检测模型可以正常转换。
Beta Was this translation helpful? Give feedback.
All reactions