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

this is a lite easy to use virtual keyboard project for anyone to use

Official implementation of deep Gaussian process (DGP)-based multi-speaker speech synthesis with PyTorch.

Efficiently computes derivatives of numpy code.

Real-time Joint Semantic Reasoning for Autonomous Driving

A new test set for ImageNet

CVPR 2021 Official Pytorch Code for UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-training

Lung Pattern Classification for Interstitial Lung Diseases Using a Deep Convolutional Neural Network

Blind Image Super-resolution with Elaborate Degradation Modeling on Noise and Kernel

Registration Loss Learning for Deep Probabilistic Point Set Registration

Performant, differentiable reinforcement learning

Rethinking the U-Net architecture for multimodal biomedical image segmentation

This is a collection of simple PyTorch implementations of neural networks and related algorithms. These implementations are documented with explanations,

DeepLab resnet v2 model in pytorch

[KDD 2021, Research Track] DiffMG: Differentiable Meta Graph Search for Heterogeneous Graph Neural Networks

A framework for the elicitation, specification, formalization and understanding of requirements.

Simultaneous Detection and Segmentation

(CVPR2021) Kaleido-BERT: Vision-Language Pre-training on Fashion Domain

[CVPR 2022 Oral] Crafting Better Contrastive Views for Siamese Representation Learning

Deepfake Scanner by Deepware.

A curated list of awesome papers for Semantic Retrieval (TOIS Accepted: Semantic Models for the First-stage Retrieval: A Comprehensive Review).