_**This resource is a subproject of [se_resnext_for_pytorch](https://ngc.nvidia.com/catalog/resources/nvidia:se_resnext_for_pytorch). Visit the parent project to download the code and get more information about the setup.**_

The SE-ResNeXt101-32x4d is a [ResNeXt101-32x4d](https://arxiv.org/pdf/1611.05431.pdf)
model with added Squeeze-and-Excitation module introduced
in [Squeeze-and-Excitation Networks](https://arxiv.org/pdf/1709.01507.pdf) paper.

The SE-ResNeXt101-32x4d model can be deployed for inference on the [NVIDIA Triton Inference Server](https://github.com/NVIDIA/triton-inference-server) using
TorchScript, ONNX Runtime or TensorRT as an execution backend.

se_resnext_for_triton_from_pytorch

Deploying high-performance inference for SE-ResNeXt101-32x4d model using NVIDIA Triton Inference Server.

SE-ResNeXt101-32x4d Triton deployment for PyTorch