Paddle2ONNX

简体中文 | English

Introduction

Paddle2ONNX enables users to convert models from PaddlePaddle to ONNX.

• Supported model format. Paddle2ONNX supports both dynamic and static computational graph of PaddlePaddle. For static computational graph, Paddle2ONNX converts PaddlePaddle models saved by API saveinferencemodel, for example IPthon example. For dynamic computational graph, it is now under experiment and more details will be released after the release of PaddlePaddle 2.0.
• Supported operators. Paddle2ONNX can stably export models to ONNX Opset 9~11, and partialy support lower version opset. More details please refer to Operator list.
• Supported models. You can find officially verified models by Paddle2ONNX in model zoo.

AIStudio Tutorials

• Export and inference ONNX model in PaddlePaddle 2.0
• How to deploy PP-OCR model using ONNX RunTime

What we can do with Paddle2ONNX

• Deploy PaddlePaddle model by ADLIK, more details
• Deploy PaddlePaddle model by OpenVINO, more details
• Deploy PaddlePaddle model by OpenCV, more details
• Deploy PaddlePaddle model by Triton, more details

Environment Dependencies

Configuration

 python >= 2.7  
 static computational graph: paddlepaddle >= 1.8.0
 dynamic computational graph: paddlepaddle >= 2.0.0
 onnx == 1.7.0 | Optional

Installation

Via Pip

 pip install paddle2onnx

From Source

 git clone https://github.com/PaddlePaddle/Paddle2ONNX.git
 cd Paddle2ONNX
 python setup.py install

Usage

Static Computational Graph

Via Command Line Tool

Uncombined PaddlePaddle model(parameters saved in different files)

paddle2onnx --model_dir paddle_model  --save_file onnx_file --opset_version 10 --enable_onnx_checker True

Combined PaddlePaddle model(parameters saved in one binary file)

paddle2onnx --model_dir paddle_model  --model_filename model_filename --params_filename params_filename --save_file onnx_file --opset_version 10 --enable_onnx_checker True

Parameters

| Parameters | Description | |----------|--------------| |--modeldir | The directory path of the paddlepaddle model saved by `paddle.fluid.io.saveinferencemodel`| |--modelfilename |[Optional] The model file name under the directory designated by

--model_dir

• Two types of PaddlePaddle models
  • Combined model, parameters saved in one binary file. --modelfilename and --paramsfilename represents the file name and parameter name under the directory designated by --modeldir. --modelfilename and --paramsfilename are valid only with parameter --modeldir.
  • Uncombined model, parameters saved in different files. Only --model_dir is needed，which contains '__model__' file and the seperated parameter files.
• Use onnxruntime to verify the Converted model
  • When using onnxruntime to verify the converted onnx model, please note that the onnxruntime and onnx versions need to match. Onnxruntime and onnx version requirements.
• If there is a prompt that OP does not support during model conversion, users are welcome to develop by themselves, please refer to the document OP Development Guide

IPython tutorials

• Convert to ONNX from static computational graph

Dynamic Computational Graph

import paddle
from paddle import nn
from paddle.static import InputSpec
import paddle2onnx as p2o

class LinearNet(nn.Layer):
    def init(self):
        super(LinearNet, self).init()
        self._linear = nn.Linear(784, 10)
def forward(self, x):
    return self._linear(x)
layer = LinearNet()
configure model inputs
x_spec = InputSpec([None, 784], 'float32', 'x')
convert model to inference mode
layer.eval()
save_path = 'onnx.save/linear_net'
p2o.dygraph2onnx(layer, save_path + '.onnx', input_spec=[x_spec])
when paddlepaddle>2.0.0, you can try:
paddle.onnx.export(layer, save_path, input_spec=[x_spec])

IPython tutorials

• Convert to ONNX from dynamic computational graph

Documents

• model zoo
• op list
• update notes

License

Apache-2.0 license.