Official Code for "Non-deep Networks"

Related tags

Deep LearningNonDeepNetworks
Overview

Non-deep Networks
arXiv:2110.07641
Ankit Goyal, Alexey Bochkovskiy, Jia Deng, Vladlen Koltun

Overview: Depth is the hallmark of DNNs. But more depth means more sequential computation and higher latency. This begs the question -- is it possible to build high-performing ``non-deep" neural networks? We show that it is. We show, for the first time, that a network with a depth of just 12 can achieve top-1 accuracy over 80% on ImageNet, 96% on CIFAR10, and 81% on CIFAR100. We also show that a network with a low-depth (12) backbone can achieve an AP of 48% on MS-COCO.

If you find our work useful, please consider citing it:

@article{goyal2021nondeep,
  title={Non-deep Networks},
  author={Goyal, Ankit and Bochkovskiy, Alexey and Deng, Jia and Koltun, Vladlen},
  journal={arXiv:2110.07641},
  year={2021}
}

Code Coming Soon!

Comments
  • when will the code of the model be released?

    when will the code of the model be released?

    I am very interested in your research, when will the code of the model be released? I saw on October 23rd that you said it would be released in 4 weeks

    opened by Dr-Goopher 6
  • When will the code be released?

    When will the code be released?

    I am very interested in your work and would like to further study. I hope you can release the code as soon as possible in your busy schedule. Thank you！

    opened by SenShu96 5
  • what is the meaning of 'Shuffle' of fusion block in Fig. A1?

    what is the meaning of 'Shuffle' of fusion block in Fig. A1?

    Hello. Thank you for your great study. I wonder the meaning of 'Shuffle' of fusion block in Fig. A1. Is it pixel shuffle layer? Please let me know the meaning of that.

    Thank you.

    opened by jhcha08 3
  • Question about SSE module

    Question about SSE module

    Hi. Figure 2b shows that there's one 1x1conv in a branch of SSE, how to match the channel of output by 1x1conv with the channel of input after shortcut? If I set the output channel of 1x1conv the same as input, the channels of the outputs by RepVGG block and SSE will not match.

    opened by Tsianmy 2
  • Really faster than ResNet? I am very confused

    Really faster than ResNet? I am very confused

    Hello, my friend, appreciate for your great work! I have tested the code on https://github.com/Pritam-N/ParNet by Pritam-N and change the ResNet code in my model by using your ParNet , but the actual time is quite slow than the paper said. My block size is [64, 128, 256, 512, 2048], and the time of "forward()" is more than 5s average while the Resnet is 0.02s in my device. I have use the time function for every line in the forward(), find that the encode stuff is the main reason. I continue write time.perf_counter() in the encode stuff, find that the "self.stream2_fusion" and "self.stream3_fusion" is the most time user. Do you know why ?

    opened by StonepageVan 1
  • fusion module, accuracy about cifar100

    fusion module, accuracy about cifar100

    1. what is your shuffle code in your fusion module?
    2. what is your model architecture in cifar-100? I just changed front two downsample modules based on the ParNet for Imagenet in the paper. But the accuracy is lower. And How do you set the LR, MILESTONES and NUM_EPOCH to meet high accuracy?
    opened by qq769852576 2
Owner
Ankit Goyal
Phd Candidate @Princeton | Works in CV and AI
Ankit Goyal
GitHub Repository
The authors' implementation of Unsupervised Adversarial Learning of 3D Human Pose from 2D Joint Locations

Unsupervised Adversarial Learning of 3D Human Pose from 2D Joint Locations This is the authors' implementation of Unsupervised Adversarial Learning of

Dwango Media Village 140 Dec 07, 2022
Pytorch implementation of Decoupled Spatial-Temporal Transformer for Video Inpainting

Decoupled Spatial-Temporal Transformer for Video Inpainting By Rui Liu, Hanming Deng, Yangyi Huang, Xiaoyu Shi, Lewei Lu, Wenxiu Sun, Xiaogang Wang, J

51 Dec 13, 2022
Flexible time series feature extraction & processing

tsflex is a toolkit for flexible time series processing & feature extraction, that is efficient and makes few assumptions about sequence data. Useful

PreDiCT.IDLab 206 Dec 28, 2022
Deep Residual Networks with 1K Layers

Deep Residual Networks with 1K Layers By Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun. Microsoft Research Asia (MSRA). Table of Contents Introduc

Kaiming He 856 Jan 06, 2023
Implementation of the state-of-the-art vision transformers with tensorflow

ViT Tensorflow This repository contains the tensorflow implementation of the state-of-the-art vision transformers (a category of computer vision model

Mohammadmahdi NouriBorji 2 Mar 16, 2022
An implementation of RetinaNet in PyTorch.

RetinaNet An implementation of RetinaNet in PyTorch. Installation Training COCO 2017 Pascal VOC Custom Dataset Evaluation Todo Credits Installation In

Conner Vercellino 297 Jan 04, 2023
Spherical CNNs

Spherical CNNs Equivariant CNNs for the sphere and SO(3) implemented in PyTorch Overview This library contains a PyTorch implementation of the rotatio

Jonas Köhler 893 Dec 28, 2022
IEEE Winter Conference on Applications of Computer Vision 2022 Accepted

SSKT(Accepted WACV2022) Concept map Dataset Image dataset CIFAR10 (torchvision) CIFAR100 (torchvision) STL10 (torchvision) Pascal VOC (torchvision) Im

1 Nov 17, 2022
Reimplementation of NeurIPS'19: "Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting" by Shu et al.

[Re] Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting Reimplementation of NeurIPS'19: "Meta-Weight-Net: Learning an Explicit Mapping

Robert Cedergren 1 Mar 13, 2020
Text to image synthesis using thought vectors

Text To Image Synthesis Using Thought Vectors This is an experimental tensorflow implementation of synthesizing images from captions using Skip Though

Paarth Neekhara 2.1k Jan 05, 2023
A implemetation of the LRCN in mxnet

A implemetation of the LRCN in mxnet ##Abstract LRCN is a combination of CNN and RNN ##Installation Download UCF101 dataset ./avi2jpg.sh to split the

44 Aug 25, 2022
Iris prediction model is used to classify iris species created julia's DecisionTree, DataFrames, JLD2, PlotlyJS and Statistics packages.

Iris Species Predictor Iris prediction is used to classify iris species using their sepal length, sepal width, petal length and petal width created us

Siva Prakash 2 Jan 06, 2022
NAACL2021 - COIL Contextualized Lexical Retriever

COIL Repo for our NAACL paper, COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List. The code covers learning

Luyu Gao 108 Dec 31, 2022
Image De-raining Using a Conditional Generative Adversarial Network

Image De-raining Using a Conditional Generative Adversarial Network [Paper Link] [Project Page] He Zhang, Vishwanath Sindagi, Vishal M. Patel In this

He Zhang 216 Dec 18, 2022
MARE - Multi-Attribute Relation Extraction

MARE - Multi-Attribute Relation Extraction Repository for the paper submission: #TODO: insert link, when available Environment Tested with Ubuntu 18.0

0 May 11, 2021
Lung Pattern Classification for Interstitial Lung Diseases Using a Deep Convolutional Neural Network

ild-cnn This is supplementary material for the manuscript: "Lung Pattern Classification for Interstitial Lung Diseases Using a Deep Convolutional Neur

22 Nov 05, 2022
Learning Continuous Image Representation with Local Implicit Image Function

LIIF This repository contains the official implementation for LIIF introduced in the following paper: Learning Continuous Image Representation with Lo

Yinbo Chen 1k Dec 25, 2022
ncnn is a high-performance neural network inference framework optimized for the mobile platform

ncnn ncnn is a high-performance neural network inference computing framework optimized for mobile platforms. ncnn is deeply considerate about deployme

Tencent 16.2k Jan 05, 2023
Omniscient Video Super-Resolution

Omniscient Video Super-Resolution This is the official code of OVSR (Omniscient Video Super-Resolution, ICCV 2021). This work is based on PFNL. Datase

36 Oct 27, 2022
This is the code for HOI Transformer

HOI Transformer Code for CVPR 2021 accepted paper End-to-End Human Object Interaction Detection with HOI Transformer. Reproduction We recomend you to

BigBangEpoch 124 Dec 29, 2022