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

Light-Head R-CNN

Code release to accompany paper "Geometry-Aware Gradient Algorithms for Neural Architecture Search."

DyStyle: Dynamic Neural Network for Multi-Attribute-Conditioned Style Editing

A Pytorch Implementation of a continuously rate adjustable learned image compression framework.

Creating Artificial Life with Reinforcement Learning

Python Multi-Agent Reinforcement Learning framework

Local Similarity Pattern and Cost Self-Reassembling for Deep Stereo Matching Networks

Turning SymPy expressions into JAX functions

PyTorch implementation for our NeurIPS 2021 Spotlight paper "Long Short-Term Transformer for Online Action Detection".

SAGE: Sensitivity-guided Adaptive Learning Rate for Transformers

Training Cifar-10 Classifier Using VGG16

Conversion between units used in magnetism

A python library for face detection and features extraction based on mediapipe library

Co-GAIL: Learning Diverse Strategies for Human-Robot Collaboration

Code and real data for the paper "Counterfactual Temporal Point Processes", available at arXiv.

Extending JAX with custom C++ and CUDA code

Efficient 6-DoF Grasp Generation in Cluttered Scenes

This is the official released code for our paper, The Emergence of Objectness: Learning Zero-Shot Segmentation from Videos

Code for the paper Learning the Predictability of the Future

Python scripts form performing stereo depth estimation using the HITNET model in ONNX.