does openvino suppout facebook Detectron2

[stone__jesse]

https://docs.openvinotoolkit.org/latest/_docs_MO_DG_prepare_model_convert_model_Convert_Model_From_ONNX.html

alexnet, densenet121, densenet161, densenet169, densenet201, resnet101, resnet152, resnet18, resnet34, resnet50, vgg11, vgg13, vgg16, vgg19Pretrained Modelsalexnet, fbresnet152, resnet101, resnet152, resnet18, resnet34, resnet152, resnet18, resnet34, resnet50, resnext101_32x4d, resnext101_64x4d, vgg11

https://github.com/facebookresearch/detectron2/blob/master/MODEL_ZOO.md

for example does openvino support   resnet-50  fpn  model transfer

and how to do ? like pytorch -> onnx   some ways  if could give me example

[JesusE_Intel]

Hi Jesse,

The OpenVINO toolkit does not support the Detectron2 model. Take a look at the supported PyTorch models here:

https://docs.openvinotoolkit.org/latest/_docs_MO_DG_prepare_model_convert_model_Convert_Model_From_ONNX.html#supported_pytorch_models_via_onnx_conversion

Note, you will need to export your pytorch model to ONNX. You can find instructions on the PyTorch documentation.

https://pytorch.org/tutorials/advanced/super_resolution_with_onnxruntime.html

Once you have your model converted to ONNX, you can use the model optimizer to convert to Intermediate Representation (IR).

Regards,

Jesus