NGC | Catalog
CatalogResourcesSE-ResNeXt101-32x4d Triton deployment for PyTorch

SE-ResNeXt101-32x4d Triton deployment for PyTorch

For downloads and more information, please view on a desktop device.
Logo for SE-ResNeXt101-32x4d Triton deployment for PyTorch

Description

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

Publisher

NVIDIA

Use Case

Classification

Framework

PyTorch

Latest Version

-

Modified

November 12, 2021

Compressed Size

0 B

This resource is a subproject of 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 model with added Squeeze-and-Excitation module introduced in Squeeze-and-Excitation Networks paper.

The SE-ResNeXt101-32x4d model can be deployed for inference on the NVIDIA Triton Inference Server using TorchScript, ONNX Runtime or TensorRT as an execution backend.