PyTorch implementation of Octave Convolution with pre-trained Oct-ResNet and Oct-MobileNet models

Last update: Dec 18, 2022

Overview

octconv.pytorch

PyTorch implementation of Octave Convolution in Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution

ResNet-50/101 on ImageNet

Architecture	LR decay strategy	Parameters	GFLOPs	Top-1 / Top-5 Accuracy (%)
ResNet-50	step (90 epochs)	25.557M	4.089	76.010 / 92.834
ResNet-50	cosine (120 epochs)	25.557M	4.089	77.150 / 93.468
Oct-ResNet-50 (alpha=0.5)	cosine (120 epochs)	25.557M	2.367	77.640 / 93.662
ResNet-101	cosine (120 epochs)	44.549M	7.801	78.898 / 94.304
Oct-ResNet-101 (alpha=0.5)	cosine (120 epochs)	44.549M	3.991	78.794 / 94.330
ResNet-152	cosine (120 epochs)	60.193M	11.514	79.234 / 94.556
Oct-ResNet-152 (alpha=0.5)	cosine (120 epochs)	60.193M	5.615	79.258 / 94.480

MobileNet V1 on ImageNet

Architecture	LR decay strategy	Parameters	FLOPs	Top-1 / Top-5 Accuracy (%)
MobileNetV1	cosine (150 epochs)	4.232M	568.7M	72.238 / 90.536
Oct-MobileNetV1	cosine (150 epochs)	4.232M	318.2M	71.254 / 89.728

Acknowledgement

Official MXNet implmentation by @cypw

Citation

@InProceedings{Chen_2019_ICCV,
author = {Chen, Yunpeng and Fan, Haoqi and Xu, Bing and Yan, Zhicheng and Kalantidis, Yannis and Rohrbach, Marcus and Yan, Shuicheng and Feng, Jiashi},
title = {Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks With Octave Convolution},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}

PyTorch implementation of Octave Convolution with pre-trained Oct-ResNet and Oct-MobileNet models

Related tags

Overview

octconv.pytorch

ResNet-50/101 on ImageNet

MobileNet V1 on ImageNet

Acknowledgement

Citation

Owner

Duo Li

Code for ICCV 2021 paper "HuMoR: 3D Human Motion Model for Robust Pose Estimation"

Simple embedding based text classifier inspired by fastText, implemented in tensorflow

Full Stack Deep Learning Labs

Official implementation of Influence-balanced Loss for Imbalanced Visual Classification in PyTorch.

Differentiable Surface Triangulation

A super lightweight Lagrangian model for calculating millions of trajectories using ERA5 data

Explaining neural decisions contrastively to alternative decisions.

Jremesh-tools - Blender addon for quad remeshing

Collection of TensorFlow2 implementations of Generative Adversarial Network varieties presented in research papers.

Extract MNIST handwritten digits dataset binary file into bmp images

RP-GAN: Stable GAN Training with Random Projections

Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression

Transformer model implemented with Pytorch

Deep Hedging Demo - An Example of Using Machine Learning for Derivative Pricing.

Reinforcement learning models in ViZDoom environment

A `Neural = Symbolic` framework for sound and complete weighted real-value logic

General Assembly Capstone: NBA Game Predictor

Code used to generate the results appearing in "Train longer, generalize better: closing the generalization gap in large batch training of neural networks"

DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.

The source code of CVPR 2019 paper "Deep Exemplar-based Video Colorization".