3.8% and 18.3% on CIFAR-10 and CIFAR-100

Overview

Wide Residual Networks

This code was used for experiments with Wide Residual Networks (BMVC 2016) http://arxiv.org/abs/1605.07146 by Sergey Zagoruyko and Nikos Komodakis.

Deep residual networks were shown to be able to scale up to thousands of layers and still have improving performance. However, each fraction of a percent of improved accuracy costs nearly doubling the number of layers, and so training very deep residual networks has a problem of diminishing feature reuse, which makes these networks very slow to train.

To tackle these problems, in this work we conduct a detailed experimental study on the architecture of ResNet blocks, based on which we propose a novel architecture where we decrease depth and increase width of residual networks. We call the resulting network structures wide residual networks (WRNs) and show that these are far superior over their commonly used thin and very deep counterparts.

For example, we demonstrate that even a simple 16-layer-deep wide residual network outperforms in accuracy and efficiency all previous deep residual networks, including thousand-layer-deep networks. We further show that WRNs achieve incredibly good results (e.g., achieving new state-of-the-art results on CIFAR-10, CIFAR-100, SVHN, COCO and substantial improvements on ImageNet) and train several times faster than pre-activation ResNets.

Update (August 2019): Pretrained ImageNet WRN models are available in torchvision 0.4 and PyTorch Hub, e.g. loading WRN-50-2:

model = torch.hub.load('pytorch/vision', 'wide_resnet50_2', pretrained=True)

Update (November 2016): We updated the paper with ImageNet, COCO and meanstd preprocessing CIFAR results. If you're comparing your method against WRN, please report correct preprocessing numbers because they give substantially different results.

tldr; ImageNet WRN-50-2-bottleneck (ResNet-50 with wider inner bottleneck 3x3 convolution) is significantly faster than ResNet-152 and has better accuracy; on CIFAR meanstd preprocessing (as in fb.resnet.torch) gives better results than ZCA whitening; on COCO wide ResNet with 34 layers outperforms even Inception-v4-based Fast-RCNN model in single model performance.

Test error (%, flip/translation augmentation, meanstd normalization, median of 5 runs) on CIFAR:

Network CIFAR-10 CIFAR-100
pre-ResNet-164 5.46 24.33
pre-ResNet-1001 4.92 22.71
WRN-28-10 4.00 19.25
WRN-28-10-dropout 3.89 18.85

Single-time runs (meanstd normalization):

Dataset network test perf.
CIFAR-10 WRN-40-10-dropout 3.8%
CIFAR-100 WRN-40-10-dropout 18.3%
SVHN WRN-16-8-dropout 1.54%
ImageNet (single crop) WRN-50-2-bottleneck 21.9% top-1, 5.79% top-5
COCO-val5k (single model) WRN-34-2 36 mAP

See http://arxiv.org/abs/1605.07146 for details.

bibtex:

@INPROCEEDINGS{Zagoruyko2016WRN,
    author = {Sergey Zagoruyko and Nikos Komodakis},
    title = {Wide Residual Networks},
    booktitle = {BMVC},
    year = {2016}}

Pretrained models

ImageNet

WRN-50-2-bottleneck (wider bottleneck), see pretrained for details
Download (263MB): https://yadi.sk/d/-8AWymOPyVZns

There are also PyTorch and Tensorflow model definitions with pretrained weights at https://github.com/szagoruyko/functional-zoo/blob/master/wide-resnet-50-2-export.ipynb

COCO

Coming

Installation

The code depends on Torch http://torch.ch. Follow instructions here and run:

luarocks install torchnet
luarocks install optnet
luarocks install iterm

For visualizing training curves we used ipython notebook with pandas and bokeh.

Usage

Dataset support

The code supports loading simple datasets in torch format. We provide the following:

To whiten CIFAR-10 and CIFAR-100 we used the following scripts https://github.com/lisa-lab/pylearn2/blob/master/pylearn2/scripts/datasets/make_cifar10_gcn_whitened.py and then converted to torch using https://gist.github.com/szagoruyko/ad2977e4b8dceb64c68ea07f6abf397b and npy to torch converter https://github.com/htwaijry/npy4th.

We are running ImageNet experiments and will update the paper and this repo soon.

Training

We provide several scripts for reproducing results in the paper. Below are several examples.

model=wide-resnet widen_factor=4 depth=40 ./scripts/train_cifar.sh

This will train WRN-40-4 on CIFAR-10 whitened (supposed to be in datasets folder). This network achieves about the same accuracy as ResNet-1001 and trains in 6 hours on a single Titan X. Log is saved to logs/wide-resnet_$RANDOM$RANDOM folder with json entries for each epoch and can be visualized with itorch/ipython later.

For reference we provide logs for this experiment and ipython notebook to visualize the results. After running it you should see these training curves:

viz

Another example:

model=wide-resnet widen_factor=10 depth=28 dropout=0.3 dataset=./datasets/cifar100_whitened.t7 ./scripts/train_cifar.sh

This network achieves 20.0% error on CIFAR-100 in about a day on a single Titan X.

Multi-GPU is supported with nGPU=n parameter.

Other models

Additional models in this repo:

Implementation details

The code evolved from https://github.com/szagoruyko/cifar.torch. To reduce memory usage we use @fmassa's optimize-net, which automatically shares output and gradient tensors between modules. This keeps memory usage below 4 Gb even for our best networks. Also, it can generate network graph plots as the one for WRN-16-2 in the end of this page.

Acknowledgements

We thank startup company VisionLabs and Eugenio Culurciello for giving us access to their clusters, without them ImageNet experiments wouldn't be possible. We also thank Adam Lerer and Sam Gross for helpful discussions. Work supported by EC project FP7-ICT-611145 ROBOSPECT.

Artifacts for paper "MMO: Meta Multi-Objectivization for Software Configuration Tuning"

MMO: Meta Multi-Objectivization for Software Configuration Tuning This repository contains the data and code for the following paper that is currently

0 Nov 17, 2021
Bot developed in Python that automates races in pegaxy.

español | português About it: This is a fork from pega-racing-bot. This bot, developed in Python, is to automate races in pegaxy. The game developers

4 Apr 08, 2022
Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks

Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks (SDPoint) This repository contains the cod

Jason Kuen 17 Jul 04, 2022
A python package for generating, analyzing and visualizing building shadows

pybdshadow Introduction pybdshadow is a python package for generating, analyzing and visualizing building shadows from large scale building geographic

Qing Yu 13 Nov 30, 2022
Pcos-prediction - Predicts the likelihood of Polycystic Ovary Syndrome based on patient attributes and symptoms

PCOS Prediction 🥼 Predicts the likelihood of Polycystic Ovary Syndrome based on

Samantha Van Seters 1 Jan 10, 2022
Official code of CVPR 2021's PLOP: Learning without Forgetting for Continual Semantic Segmentation

PLOP: Learning without Forgetting for Continual Semantic Segmentation This repository contains all of our code. It is a modified version of Cermelli e

Arthur Douillard 116 Dec 14, 2022
Face Detection and Alignment using Multi-task Cascaded Convolutional Networks (MTCNN)

Face-Detection-with-MTCNN Face detection is a computer vision problem that involves finding faces in photos. It is a trivial problem for humans to sol

Chetan Hirapara 3 Oct 07, 2022
Pytorch implementations of popular off-policy multi-agent reinforcement learning algorithms, including QMix, VDN, MADDPG, and MATD3.

Off-Policy Multi-Agent Reinforcement Learning (MARL) Algorithms This repository contains implementations of various off-policy multi-agent reinforceme

183 Dec 28, 2022
A library for researching neural networks compression and acceleration methods.

A library for researching neural networks compression and acceleration methods.

Intel Labs 100 Dec 29, 2022
Experimental code for paper: Generative Adversarial Networks as Variational Training of Energy Based Models

Experimental code for paper: Generative Adversarial Networks as Variational Training of Energy Based Models, under review at ICLR 2017 requirements: T

Shuangfei Zhai 18 Mar 05, 2022
Predict and time series avocado hass

RECOMMENDER SYSTEM MARKETING TỔNG QUAN VỀ HỆ THỐNG DỮ LIỆU 1. Giới thiệu - Tiki là một hệ sinh thái thương mại "all in one", trong đó có tiki.vn, là

hieulmsc 3 Jan 10, 2022
[ICLR2021] Unlearnable Examples: Making Personal Data Unexploitable

Unlearnable Examples Code for ICLR2021 Spotlight Paper "Unlearnable Examples: Making Personal Data Unexploitable " by Hanxun Huang, Xingjun Ma, Sarah

Hanxun Huang 98 Dec 07, 2022
Course about deep learning for computer vision and graphics co-developed by YSDA and Skoltech.

Deep Vision and Graphics This repo supplements course "Deep Vision and Graphics" taught at YSDA @fall'21. The course is the successor of "Deep Learnin

Yandex School of Data Analysis 160 Jan 02, 2023
JudeasRx - graphical app for doing personalized causal medicine using the methods invented by Judea Pearl et al.

JudeasRX Instructions Read the references given in the Theory and Notation section below Fire up the Jupyter Notebook judeas-rx.ipynb The notebook dra

Robert R. Tucci 19 Nov 07, 2022
Code for generating a single image pretraining dataset

Single Image Pretraining of Visual Representations As shown in the paper A critical analysis of self-supervision, or what we can learn from a single i

Yuki M. Asano 12 Dec 19, 2022
Neural Architecture Search Powered by Swarm Intelligence 🐜

Neural Architecture Search Powered by Swarm Intelligence 🐜 DeepSwarm DeepSwarm is an open-source library which uses Ant Colony Optimization to tackle

288 Oct 28, 2022
SeqFormer: a Frustratingly Simple Model for Video Instance Segmentation

SeqFormer: a Frustratingly Simple Model for Video Instance Segmentation SeqFormer SeqFormer: a Frustratingly Simple Model for Video Instance Segmentat

Junfeng Wu 298 Dec 22, 2022
Prometheus Exporter for data scraped from datenplattform.darmstadt.de

darmstadt-opendata-exporter Scrapes data from https://datenplattform.darmstadt.de and presents it in the Prometheus Exposition format. Pull requests w

Martin Weinelt 2 Apr 12, 2022
GLM (General Language Model)

GLM GLM is a General Language Model pretrained with an autoregressive blank-filling objective and can be finetuned on various natural language underst

THUDM 421 Jan 04, 2023
Discovering and Achieving Goals via World Models

Discovering and Achieving Goals via World Models [Project Website] [Benchmark Code] [Video (2min)] [Oral Talk (13min)] [Paper] Russell Mendonca*1, Ole

Oleg Rybkin 71 Dec 22, 2022