Pytorch implementation of AngularGrad: A New Optimization Technique for Angular Convergence of Convolutional Neural Networks

Last update: Sep 16, 2022

Related tags

Deep Learning AngularGrad

Overview

AngularGrad Optimizer

This repository contains the oficial implementation for AngularGrad: A New Optimization Technique for Angular Convergence of Convolutional Neural Networks in PyTorch.

AngularGrad reduces the zig-zag effect in the optimization trajectory. Fluctuations are significantly smoothed, tracing a more direct path towards the minimum of the cost function.

If you have questions or suggestions, please feel free to open an issue. Please cite as:

@article{roy2021angulargrad,
  title={AngularGrad: A New Optimization Technique for Angular Convergence of Convolutional Neural Networks},
  author={S.K. Roy, M.E. Paoletti, J.M. Haut, S.R. Dubey, P. Kar, A. Plaza and B.B. Chaudhuri},
  journal={arXiv preprint arXiv:2105.10190},
  year={2021}
}

In PyTorch:

optimizer = cosangulargrad(params, lr=1e-3, betas=(0.9, 0.999), eps=1e-8, weight_decay=0)
<or>
optimizer = tanangulargrad(params, lr=1e-3, betas=(0.9, 0.999), eps=1e-8, weight_decay=0)
Example:
optimizer = cosangulargrad(net.parameters())

Experiments

Experiments in the paper:

Analitycal

cd analitycal/
python main.py

CIFAR-10/100

cd cifar/
python main.py --dataset <cifar10/cifar100> --model <r18/r34/.../vgg16/d121> --alg <adam/sgd/.../cosangulargrad/tanangulargrad> --lr <float>
Example:
python main.py --dataset cifar10 --model r50 --alg cosangulargrad --lr 1e-3

Mini-ImageNet:

cd mini-imagenet/
wget URL dataset
python main.py DATADIR --alg <adam/sgd/.../cosangulargrad/tanangulargrad> --lr <float>
Example:
python main.py ./split_mini/ --alg cosangulargrad --model r50 --lr 1e-3

Fine-Grained:

cd fine-grained/
wget URL datasets
python main.py DATADIR --dataset <dsetname> --alg <adam/sgd/.../cosangulargrad/tanangulargrad> --lr <float>
Example:
python main.py ./data/Car196/ --dataset cars --alg adam --lr 1e-3

Pytorch implementation of AngularGrad: A New Optimization Technique for Angular Convergence of Convolutional Neural Networks

Related tags

Overview

AngularGrad Optimizer

Experiments

Owner

mario

EMNLP'2021: Simple Entity-centric Questions Challenge Dense Retrievers

SimulLR - PyTorch Implementation of SimulLR

Unofficial PyTorch implementation of "RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving" (ECCV 2020)

Code from PropMix, accepted at BMVC'21

PyTorch Code for NeurIPS 2021 paper Anti-Backdoor Learning: Training Clean Models on Poisoned Data.

Official implementation of the paper ``Unifying Nonlocal Blocks for Neural Networks'' (ICCV'21)

Accurate identification of bacteriophages from metagenomic data using Transformer

CPF: Learning a Contact Potential Field to Model the Hand-object Interaction

DPC: Unsupervised Deep Point Correspondence via Cross and Self Construction (3DV 2021)

Sdf sparse conv - Deep Learning on SDF for Classifying Brain Biomarkers

[NeurIPS 2021] Garment4D: Garment Reconstruction from Point Cloud Sequences

Trading environnement for RL agents, backtesting and training.

📖 Deep Attentional Guided Image Filtering

RANZCR-CLiP 7th Place Solution

Augmented CLIP - Training simple models to predict CLIP image embeddings from text embeddings, and vice versa.

OpenABC-D: A Large-Scale Dataset For Machine Learning Guided Integrated Circuit Synthesis

This is the repository for Learning to Generate Piano Music With Sustain Pedals

Towards Part-Based Understanding of RGB-D Scans

FCA: Learning a 3D Full-coverage Vehicle Camouflage for Multi-view Physical Adversarial Attack

A Nim frontend for pytorch, aiming to be mostly auto-generated and internally using ATen.