How Do Adam and Training Strategies Help BNNs Optimization? In ICML 2021.

Related tags

Deep Learning AdamBNN
Overview

AdamBNN

This is the pytorch implementation of our paper "How Do Adam and Training Strategies Help BNNs Optimization?", published in ICML 2021.

In this work, we explore the intrisic reasons why Adam is superior to other optimizers like SGD for BNN optimization and provide analytical explanations that support specific training strategies. By visualizing the optimization trajectory, we show that the optimization lies in extremely rugged loss landscape and the second-order momentum in Adam is crucial to revitalize the weights that are dead due to the activation saturation in BNNs. Based on analysis, we derive a specific training scheme and achieve 70.5% top-1 accuracy on the ImageNet dataset using the same achitecture as ReActNet while achieving 1.1% higher accuracy.

Citation

If you find our code useful for your research, please consider citing:

@conference{liu2021how,
title = {How do adam and training strategies help bnns optimization?},
author = {Liu, Zechun and Shen, Zhiqiang and Li, Shichao and Helwegen, Koen and Huang, Dong and Cheng, Kwang-Ting},
booktitle = {International Conference on Machine Learning},
year = {2021},
organization={PMLR}
}

Run

1. Requirements:

  • python3, pytorch 1.7.1, torchvision 0.8.2

2. Data:

  • Download ImageNet dataset

3. Steps to run:

(1) Step1: binarizing activations

  • Change directory to ./step1/
  • run bash run.sh

(2) Step2: binarizing weights + activations

  • Change directory to ./step2/
  • run bash run.sh

Models

Methods Backbone Top1-Acc FLOPs Trained Model
ReActNet ReActNet-A 69.4% 0.87 x 10^8 Model-ReAct
AdamBNN ReActNet-A 70.5% 0.87 x 10^8 Model-ReAct-AdamBNN-Training

Contact

Zechun Liu, HKUST and CMU (zliubq at connect.ust.hk / zechunl at andrew.cmu.edu)

Zhiqiang Shen, CMU (zhiqians at andrew.cmu.edu)

You might also like...
Official Code for ICML 2021 paper
Official Code for ICML 2021 paper "Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline"

Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline Ankit Goyal, Hei Law, Bowei Liu, Alejandro Newell, Jia Deng Internati

Princeton Vision & Learning Lab 115 Jan 4, 2023
Implementation of Self-supervised Graph-level Representation Learning with Local and Global Structure (ICML 2021).
Implementation of Self-supervised Graph-level Representation Learning with Local and Global Structure (ICML 2021).

Self-supervised Graph-level Representation Learning with Local and Global Structure Introduction This project is an implementation of ``Self-supervise

MilaGraph 50 Dec 9, 2022
[ICML 2021] Towards Understanding and Mitigating Social Biases in Language Models

Towards Understanding and Mitigating Social Biases in Language Models This repo contains code and data for evaluating and mitigating bias from generat

Paul Liang 42 Jan 3, 2023
Supplementary code for SIGGRAPH 2021 paper: Discovering Diverse Athletic Jumping Strategies
Supplementary code for SIGGRAPH 2021 paper: Discovering Diverse Athletic Jumping Strategies

SIGGRAPH 2021: Discovering Diverse Athletic Jumping Strategies project page paper demo video Prerequisites Important Notes We suspect there are bugs i

null 54 Dec 6, 2022
Racing line optimization algorithm in python that uses Particle Swarm Optimization.
Racing line optimization algorithm in python that uses Particle Swarm Optimization.

Racing Line Optimization with PSO This repository contains a racing line optimization algorithm in python that uses Particle Swarm Optimization. Requi

Parsa Dahesh 6 Dec 14, 2022
Code for ICML 2021 paper: How could Neural Networks understand Programs?
Code for ICML 2021 paper: How could Neural Networks understand Programs?

OSCAR This repository contains the source code of our ICML 2021 paper How could Neural Networks understand Programs?. Environment Run following comman

Dinglan Peng 115 Dec 17, 2022
[ICML 2021, Long Talk] Delving into Deep Imbalanced Regression
[ICML 2021, Long Talk] Delving into Deep Imbalanced Regression

Delving into Deep Imbalanced Regression This repository contains the implementation code for paper: Delving into Deep Imbalanced Regression Yuzhe Yang

Yuzhe Yang 568 Dec 30, 2022
[ICML 2021] DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning | 斗地主AI
[ICML 2021] DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning | 斗地主AI

[ICML 2021] DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning DouZero is a reinforcement learning framework for DouDizhu (斗地主), t

Kwai Inc. 3.1k Jan 4, 2023
An interpreter for RASP as described in the ICML 2021 paper "Thinking Like Transformers"

RASP Setup Mac or Linux Run ./setup.sh . It will create a python3 virtual environment and install the dependencies for RASP. It will also try to insta

null 141 Jan 3, 2023
Comments
  • Can you provide the model files for the first stage?

    Can you provide the model files for the first stage?

    I paid attention to your work very early and I admire you very much. I want to train from the second stage, so I would like to ask if you can provide the first stage model?

    opened by 17818587795 3
  • Question about visualization

    Question about visualization

    Thanks Zechun! Very interesting work!

    Could you provide the code about Figure. 1, i.e. "the actual optimization landscape from real-valued and binary networks with the same architecture"

    Thanks a lot!

    opened by techmonsterwang 0
Owner
Zechun Liu
Ph.D student in HKUST and visiting scholar in CMU
Zechun Liu
GitHub
PyTorch implementation of our Adam-NSCL algorithm from our CVPR2021 (oral) paper "Training Networks in Null Space for Continual Learning"

Adam-NSCL This is a PyTorch implementation of Adam-NSCL algorithm for continual learning from our CVPR2021 (oral) paper: Title: Training Networks in N

Shipeng Wang 34 Dec 21, 2022
Ranger - a synergistic optimizer using RAdam (Rectified Adam), Gradient Centralization and LookAhead in one codebase

Ranger-Deep-Learning-Optimizer Ranger - a synergistic optimizer combining RAdam (Rectified Adam) and LookAhead, and now GC (gradient centralization) i

Less Wright 1.1k Dec 21, 2022
This is the official PyTorch implementation of the paper "TransFG: A Transformer Architecture for Fine-grained Recognition" (Ju He, Jie-Neng Chen, Shuai Liu, Adam Kortylewski, Cheng Yang, Yutong Bai, Changhu Wang, Alan Yuille).

TransFG: A Transformer Architecture for Fine-grained Recognition Official PyTorch code for the paper: TransFG: A Transformer Architecture for Fine-gra

Ju He 307 Jan 3, 2023
Code for the ICML 2021 paper "Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation", Haoxiang Wang, Han Zhao, Bo Li.

Bridging Multi-Task Learning and Meta-Learning Code for the ICML 2021 paper "Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Trainin

AI Secure 57 Dec 15, 2022
Code for paper "Which Training Methods for GANs do actually Converge? (ICML 2018)"

GAN stability This repository contains the experiments in the supplementary material for the paper Which Training Methods for GANs do actually Converg

Lars Mescheder 885 Jan 1, 2023
FuseDream: Training-Free Text-to-Image Generationwith Improved CLIP+GAN Space OptimizationFuseDream: Training-Free Text-to-Image Generationwith Improved CLIP+GAN Space Optimization

FuseDream This repo contains code for our paper (paper link): FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space Optimizat

XCL 191 Dec 31, 2022
Genetic Algorithm, Particle Swarm Optimization, Simulated Annealing, Ant Colony Optimization Algorithm,Immune Algorithm, Artificial Fish Swarm Algorithm, Differential Evolution and TSP(Traveling salesman)

scikit-opt Swarm Intelligence in Python (Genetic Algorithm, Particle Swarm Optimization, Simulated Annealing, Ant Colony Algorithm, Immune Algorithm,A

郭飞 3.7k Jan 3, 2023
library for nonlinear optimization, wrapping many algorithms for global and local, constrained or unconstrained, optimization

NLopt is a library for nonlinear local and global optimization, for functions with and without gradient information. It is designed as a simple, unifi

Steven G. Johnson 1.4k Dec 25, 2022
Code for the ICML 2021 paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"

ViLT Code for the paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision" Install pip install -r requirements.txt pip

Wonjae Kim 922 Jan 1, 2023
Code for the ICML 2021 paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision"

ViLT Code for the paper: "ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision" Install pip install -r requirements.txt pip

Wonjae Kim 922 Jan 1, 2023