https://github.com/JordanAsh/boostresnet

A PyTorch implementation of BoostResNet
https://github.com/JordanAsh/boostresnet

Last synced: about 2 months ago
JSON representation

A PyTorch implementation of BoostResNet

• Host: GitHub
• URL: https://github.com/JordanAsh/boostresnet
• Owner: JordanAsh
• Created: 2018-03-03T05:58:03.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2018-03-03T06:36:19.000Z (over 6 years ago)
• Last Synced: 2024-07-02T09:17:50.029Z (3 months ago)
• Language: Python
• Homepage:
• Size: 2.61 MB
• Stars: 5
• Watchers: 3
• Forks: 4
• Open Issues: 4
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome-gradient-boosting-papers - [Code

README

        
# BoostResNet

This repository contains a simple PyTorch implementation of the article [Learning Deep ResNet Blocks Sequentially using Boosting Theory](https://arxiv.org/abs/1706.04964).

The program `brn.py` assumes the existence of a dataset in torch format that is already normalized. It uses a 50-layer ResNet architecture from [Facebook](https://github.com/facebook/fb.resnet.torch) that takes 32 x 32 images as input, but can easily be modified to accomodate other architectures. 

`python brn.py --data CIFAR.t7 --transform`