PyTorch* framework is supported through export to ONNX* format. A summary of the steps for optimizing and deploying a model that was trained with the PyTorch* framework:
- Export PyTorch model to ONNX*.
- Configure the Model Optimizer for ONNX*.
- Convert an ONNX\* model to produce an optimized Intermediate Representation (IR) of the model based on the trained network topology, weights, and biases values.
- Test the model in the Intermediate Representation format using the Inference Engine in the target environment via provided sample applications.
- Integrate the Inference Engine in your application to deploy the model in the target environment.
Here is the list of models that were tested and are guaranteed to be supported. It is not a full list of models that can be converted to ONNX* and to IR.
|Package Name ||Supported Models |
|Torchvision Models ||alexnet, densenet121, densenet161, densenet169, densenet201, resnet101, resnet152, resnet18, resnet34, resnet50, vgg11, vgg13, vgg16, vgg19 |
|Pretrained Models ||alexnet, fbresnet152, resnet101, resnet152, resnet18, resnet34, resnet152, resnet18, resnet34, resnet50, resnext101_32x4d, resnext101_64x4d, vgg11 |
Other supported topologies
Export PyTorch* Model to ONNX* Format
PyTorch models are defined in a Python* code, to export such models use
torch.onnx.export() method. Only the basics will be covered here, the step to export to ONNX* is crucial but it is covered by PyTorch* framework. For more information, please refer to PyTorch* documentation.
To export a PyTorch* model you need to obtain the model as an instance of
torch.nn.Module class and call the
# Instantiate your model. This is just a regular PyTorch model that will be exported in the following steps.
model = SomeModel()
# Evaluate the model to switch some operations from training mode to inference.
# Create dummy input for the model. It will be used to run the model inside export function.
dummy_input = torch.randn(1, 3, 224, 224)
# Call the export function
torch.onnx.export(model, (dummy_input, ), 'model.onnx')
- Not all PyTorch* operations can be exported to ONNX* opset 9 which is used by default, as of version 1.8.1. It is recommended to export models to opset 11 or higher when export to default opset 9 is not working. In that case, use
opset_version option of the
torch.onnx.export. For more information about ONNX* opset, refer to the Operator Schemas.