New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

CPPD模型导出onnx模型后精度损失较大 #1442

Open

EzcodingSen opened this issue Nov 21, 2024 · 1 comment

EzcodingSen commented Nov 21, 2024

问题描述
我使用的是文本识别模型CPPD_base_ch，在同一批图片上进行文本识别：

tools/infer_rec.py使用best_accuracy.pdparams进行预测
导出onnx模型后
tools/infer/predict_rec.py使用onnx模型进行推理
二者得到的结果差别很大，且onnx推理结果置信度都较低，有较大精度损失

更多信息 :

用于部署的推理引擎: onnxruntim
为什么需要转换为ONNX格式：玩
Paddle2ONNX版本: lastest
你的联系方式(Email/Wechat/Phone): [email protected]

报错截图
onnx推理：

pdparam预测：

其他信息

Collaborator

Zheng-Bicheng commented Nov 22, 2024

有算过cos相似度嘛？

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment