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
⚓ Eurybia monitor model drift over time and securize model deployment with data validation

View Demo · Documentation · Medium article 🔍 Overview Eurybia is a Python library which aims to help in : Detecting data drift and model drift Valida

MAIF 172 Dec 27, 2022
Build a medical knowledge graph based on Unified Language Medical System (UMLS)

UMLS-Graph Build a medical knowledge graph based on Unified Language Medical System (UMLS) Requisite Install MySQL Server 5.6 and import UMLS data int

Donghua Chen 6 Dec 25, 2022
Code & Data for the Paper "Time Masking for Temporal Language Models", WSDM 2022

Time Masking for Temporal Language Models This repository provides a reference implementation of the paper: Time Masking for Temporal Language Models

Guy Rosin 12 Jan 06, 2023
A JAX-based research framework for writing differentiable numerical simulators with arbitrary discretizations

jaxdf - JAX-based Discretization Framework Overview | Example | Installation | Documentation ⚠️ This library is still in development. Breaking changes

UCL Biomedical Ultrasound Group 65 Dec 23, 2022
Unsupervised Image-to-Image Translation

UNIT: UNsupervised Image-to-image Translation Networks Imaginaire Repository We have a reimplementation of the UNIT method that is more performant. It

Ming-Yu Liu 劉洺堉 1.9k Dec 26, 2022
FIGARO: Generating Symbolic Music with Fine-Grained Artistic Control

FIGARO: Generating Symbolic Music with Fine-Grained Artistic Control by Dimitri von Rütte, Luca Biggio, Yannic Kilcher, Thomas Hofmann FIGARO: Generat

Dimitri 83 Jan 07, 2023
ExCon: Explanation-driven Supervised Contrastive Learning

ExCon: Explanation-driven Supervised Contrastive Learning Link to the paper: https://arxiv.org/pdf/2111.14271.pdf Contributors of this repo: Zhibo Zha

Zhibo (Darren) Zhang 18 Nov 01, 2022
这是一个yolox-keras的源码，可以用于训练自己的模型。

YOLOX：You Only Look Once目标检测模型在Keras当中的实现 目录 性能情况 Performance 实现的内容 Achievement 所需环境 Environment 小技巧的设置 TricksSet 文件下载 Download 训练步骤 How2train 预测步骤 Ho

Bubbliiiing 64 Nov 10, 2022
A package for "Procedural Content Generation via Reinforcement Learning" OpenAI Gym interface.

Readme: Illuminating Diverse Neural Cellular Automata for Level Generation This is the codebase used to generate the results presented in the paper av

Sam Earle 27 Jan 05, 2023
RRL: Resnet as representation for Reinforcement Learning

Resnet as representation for Reinforcement Learning (RRL) is a simple yet effective approach for training behaviors directly from visual inputs. We demonstrate that features learned by standard image

Meta Research 21 Dec 07, 2022
Official code release for: EditGAN: High-Precision Semantic Image Editing

Official code release for: EditGAN: High-Precision Semantic Image Editing

565 Jan 05, 2023
Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weather

LiDAR fog simulation Created by Martin Hahner at the Computer Vision Lab of ETH Zurich. This is the official code release of the paper Fog Simulation

Martin Hahner 110 Dec 30, 2022
【Arxiv】Exploring Separable Attention for Multi-Contrast MR Image Super-Resolution

SANet Exploring Separable Attention for Multi-Contrast MR Image Super-Resolution Dependencies numpy==1.18.5 scikit_image==0.16.2 torchvision==0.8.1 to

36 Jan 05, 2023
Deep learning (neural network) based remote photoplethysmography: how to extract pulse signal from video using deep learning tools

Deep-rPPG: Camera-based pulse estimation using deep learning tools Deep learning (neural network) based remote photoplethysmography: how to extract pu

Terbe Dániel 138 Dec 17, 2022
Clustering is a popular approach to detect patterns in unlabeled data

Visual Clustering Clustering is a popular approach to detect patterns in unlabeled data. Existing clustering methods typically treat samples in a data

Tarek Naous 24 Nov 11, 2022
NCVX (NonConVeX): A User-Friendly and Scalable Package for Nonconvex Optimization in Machine Learning.

NCVX NCVX: A User-Friendly and Scalable Package for Nonconvex Optimization in Machine Learning. Please check https://ncvx.org for detailed instruction

SUN Group @ UMN 28 Aug 03, 2022
Several simple examples for popular neural network toolkits calling custom CUDA operators.

Neural Network CUDA Example Several simple examples for neural network toolkits (PyTorch, TensorFlow, etc.) calling custom CUDA operators. We provide

WeiYang 798 Jan 01, 2023
Official repo for our 3DV 2021 paper "Monocular 3D Reconstruction of Interacting Hands via Collision-Aware Factorized Refinements".

Monocular 3D Reconstruction of Interacting Hands via Collision-Aware Factorized Refinements Yu Rong, Jingbo Wang, Ziwei Liu, Chen Change Loy Paper. Pr

Yu Rong 41 Dec 13, 2022
Dense Deep Unfolding Network with 3D-CNN Prior for Snapshot Compressive Imaging, ICCV2021 [PyTorch Code]

Dense Deep Unfolding Network with 3D-CNN Prior for Snapshot Compressive Imaging, ICCV2021 [PyTorch Code]

Jian Zhang 20 Oct 24, 2022
RM Operation can equivalently convert ResNet to VGG, which is better for pruning; and can help RepVGG perform better when the depth is large.

RM Operation can equivalently convert ResNet to VGG, which is better for pruning; and can help RepVGG perform better when the depth is large.

184 Jan 04, 2023