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

PyTorch code for our paper "Image Super-Resolution with Non-Local Sparse Attention" (CVPR2021).

implementation for paper "ShelfNet for fast semantic segmentation"

Code, final versions, and information on the Sparkfun Graphical Datasheets

TensorFlow Implementation of Unsupervised Cross-Domain Image Generation

ONNX-GLPDepth - Python scripts for performing monocular depth estimation using the GLPDepth model in ONNX

Image Fusion Transformer

(NeurIPS '21 Spotlight) IQ-Learn: Inverse Q-Learning for Imitation

Official repository for the paper, MidiBERT-Piano: Large-scale Pre-training for Symbolic Music Understanding.

A hue shift helper for OBS

Uncertainty Estimation via Response Scaling for Pseudo-mask Noise Mitigation in Weakly-supervised Semantic Segmentation

This repository is dedicated to developing and maintaining code for experiments with wide neural networks.

Pytorch codes for Feature Transfer Learning for Face Recognition with Under-Represented Data

Official implementation of "A Unified Objective for Novel Class Discovery", ICCV2021 (Oral)

Lucid Sonic Dreams syncs GAN-generated visuals to music.

Code release for NeX: Real-time View Synthesis with Neural Basis Expansion

PyTorch implementation of neural style randomization for data augmentation

This is the code for "HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields".

A python script to convert images to animated sus among us crewmate twerk jifs as seen on r/196

OoD Minimum Anomaly Score GAN - Code for the Paper 'OMASGAN: Out-of-Distribution Minimum Anomaly Score GAN for Sample Generation on the Boundary'

PFLD pytorch Implementation