简体中文 | English
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 save_inference_model, 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.
python >= 2.7
static computational graph: paddlepaddle >= 1.8.0
dynamic computational graph: paddlepaddle >= 2.0.0
onnx == 1.7.0 | Optional
pip install paddle2onnx
git clone https://github.com/PaddlePaddle/paddle2onnx.git
python setup.py install
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 | Description |
|---|---|
| --model_dir | the directory path of the paddlepaddle model saved by paddle.fluid.io.save_inference_model |
| --model_filename | [Optional] the model file name under the directory designated by--model_dir. Only needed when all the model parameters saved in one binary file. Default value None |
| --params_filename | [Optonal] the parameter file name under the directory designated by--model_dir. Only needed when all the model parameters saved in one binary file. Default value None |
| --save_file | the directory path for the exported ONNX model |
| --opset_version | [Optional] To configure the ONNX Opset version. Opset 9-11 are stably supported. Default value is 9. |
| --enable_onnx_checker | [Optional] To check the validity of the exported ONNX model. It is suggested to turn on the switch. If set to True, onnx>=1.7.0 is required. Default value is False |
| --version | [Optional] check the version of paddle2onnx |
- Two types of PaddlePaddle models
- Combined model, parameters saved in one binary file. --model_filename and --params_filename represents the file name and parameter name under the directory designated by --model_dir. --model_filename and --params_filename are valid only with parameter --model_dir.
- Uncombined model, parameters saved in different files. Only --model_dir is needed，which contains '__model__' file and the seperated parameter files.
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])