ONNX* is a representation format for deep learning models. ONNX allows AI developers easily transfer models between different frameworks that helps to choose the best combination for them. Today, PyTorch*, Caffe2*, Apache MXNet*, Microsoft Cognitive Toolkit* and other tools are developing ONNX support.
Model Name | Path to Public Models master branch |
---|---|
bvlc_alexnet | model archive |
bvlc_googlenet | model archive |
bvlc_reference_caffenet | model archive |
bvlc_reference_rcnn_ilsvrc13 | model archive |
inception_v1 | model archive |
inception_v2 | model archive |
resnet50 | model archive |
squeezenet | model archive |
densenet121 | model archive |
emotion_ferplus | model archive |
mnist | model archive |
shufflenet | model archive |
VGG19 | model archive |
zfnet512 | model archive |
Listed models are built with operation set version 8. Models that are upgraded to higher operation set versions may not be supported.
Starting from the R4 release, the OpenVINO™ toolkit officially supports public Pytorch* models (from torchvision
0.2.1 and pretrainedmodels
0.7.4 packages) via ONNX conversion. The list of supported topologies is presented below:
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 |
Starting from the R5 release, the OpenVINO™ toolkit officially supports public PaddlePaddle* models via ONNX conversion. The list of supported topologies is presented below:
Model Name | Path to Model Code |
---|---|
fit_a_line | model code |
recognize_digits | model code |
VGG16 | model code |
ResNet | model code |
MobileNet | model code |
SE_ResNeXt | model code |
Inception-v4 | model code |
The Model Optimizer process assumes you have an ONNX model that was directly downloaded from a public repository or converted from any framework that supports exporting to the ONNX format.
To convert an ONNX* model:
<INSTALL_DIR>/deployment_tools/model_optimizer
directory.mo.py
script to simply convert a model with the path to the input model .nnet
file: There are no ONNX* specific parameters, so only framework-agnostic parameters are available to convert your model.
Refer to Supported Framework Layers for the list of supported standard layers.