facebookresearch/ResNeXt
ResNeXt is a deep neural network architecture for image classification using aggregated residual transformations, implemented in Torch/Lua.
Not currently ranked — collecting fresh signals.
star history
This repository provides a Torch implementation of the ResNeXt algorithm for image classification, based on the paper by Xie et al. The architecture constructs networks by repeating building blocks that aggregate a set of transformations with the same topology, exposing a new dimension called cardinality. The code is based on fb.resnet.torch and includes pretrained ImageNet models.
Frequently asked
- What is facebookresearch/ResNeXt?
- ResNeXt is a deep neural network architecture for image classification using aggregated residual transformations, implemented in Torch/Lua.
- Is ResNeXt open source?
- Yes — facebookresearch/ResNeXt is an open-source project tracked on heatdrop.
- What language is ResNeXt written in?
- facebookresearch/ResNeXt is primarily written in Lua.
- How popular is ResNeXt?
- facebookresearch/ResNeXt has 1.9k stars on GitHub.
- Where can I find ResNeXt?
- facebookresearch/ResNeXt is on GitHub at https://github.com/facebookresearch/ResNeXt.