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

A PyTorch implementation of the Transformer model in "Attention is All You Need".

Real-Time-Student-Attendence-System - Real Time Student Attendence System

GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond

DeepFaceLive - Live Deep Fake in python, Real-time face swap for PC streaming or video calls

Official codebase for Decision Transformer: Reinforcement Learning via Sequence Modeling.

Learning Neural Painters Fast! using PyTorch and Fast.ai

This repo contains the official code of our work SAM-SLR which won the CVPR 2021 Challenge on Large Scale Signer Independent Isolated Sign Language Recognition.

Code release for NeurIPS 2020 paper "Co-Tuning for Transfer Learning"

Gesture Volume Control v.2

Directed Greybox Fuzzing with AFL

Codebase for Time-series Generative Adversarial Networks (TimeGAN)

OCTIS: Comparing Topic Models is Simple! A python package to optimize and evaluate topic models (accepted at EACL2021 demo track)

Toontown House CT Edition

PyTorch implementation of DreamerV2 model-based RL algorithm

Implementation of Hierarchical Transformer Memory (HTM) for Pytorch

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

Melanoma Skin Cancer Detection using Convolutional Neural Networks and Transfer Learning🕵🏻‍♂️

Gems & Holiday Package Prediction

Repository for tackling Kaggle Ultrasound Nerve Segmentation challenge using Torchnet.

Multi-Stage Spatial-Temporal Convolutional Neural Network (MS-GCN)