English | 简体中文
After training the model by PaddleSeg, we also support exporting model with ONNX format. This tutorial provides an example to introduce it.
For the complete method of exporting ONNX format models, please refer to Paddle2ONNX。
Refer to document to export model, and save the exported inference model to the output folder, as follows.
./output
├── deploy.yaml # deployment-related profile
├── model.pdmodel # topology file of inference model
├── model.pdiparams # weight file of inference model
└── model.pdiparams.info # additional information, generally do not need attention to this file
Install Paddle2ONNX (version 0.6 or higher).
pip install paddle2onnx
Execute the following command to export the prediction model in the output folder to an ONNX format model by Paddle2ONNX.
paddle2onnx --model_dir output \
--model_filename model.pdmodel \
--params_filename model.pdiparams \
--opset_version 11 \
--save_file output.onnx
The exported ONNX format model is saved as output.onnx file.
Reference documents:
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》