Pytorch implementation of COIN, a framework for compression with implicit neural representations ๐ŸŒธ

Related tags

Deep Learningcoin
Overview

COIN ๐ŸŒŸ

This repo contains a Pytorch implementation of COIN: COmpression with Implicit Neural representations, including code to reproduce all experiments and plots in the paper.

Requirements

We ran our experiments with python 3.8.7 using torch 1.7.0 and torchvision 0.8.0 but the code is likely to work with earlier versions too. All requirements can be installed with

pip install -r requirements.txt

Usage

Compression

To compress the image kodak-dataset/kodim15.png, run

python main.py -ld logs_dir

This will save the COIN model and the reconstruction of the image (as well as logs of the losses and PSNR) to the logs_dir directory. To run on a specific image in the Kodak dataset, add the -iid flag. For example, to compress image 3, run

python main.py -ld logs_dir -iid 3

To compress the entire Kodak dataset, run

python main.py -ld logs_dir -fd

NOTE: The half precision version of torch.sin is only implemented in CUDA, so the half precision models can only be run on GPU, you need that to reproduce the results from the paper.

To reproduce the results from the paper, run the architectures listed in Appendix A

python main.py -ld logs_dir -fd --num_layers 5 --layer_size 20
python main.py -ld logs_dir -fd --num_layers 5 --layer_size 30
python main.py -ld logs_dir -fd --num_layers 10 --layer_size 28
python main.py -ld logs_dir -fd --num_layers 10 --layer_size 40
python main.py -ld logs_dir -fd --num_layers 13 --layer_size 49

Plots

To recreate plots from the paper, run

python plots.py

See the plots.py file to customize plots.

Acknowledgements

Our benchmarks and plots are based on the CompressAI library. Our SIREN implementation is based on lucidrains' implementation.

License

MIT

Owner
Emilien Dupont
Machine Learning is coolbeans ๐ŸŒด twitter.com/emidup
Emilien Dupont
Designing a Practical Degradation Model for Deep Blind Image Super-Resolution (ICCV, 2021) (PyTorch) - We released the training code!

Designing a Practical Degradation Model for Deep Blind Image Super-Resolution Kai Zhang, Jingyun Liang, Luc Van Gool, Radu Timofte Computer Vision Lab

Kai Zhang 804 Jan 08, 2023
Paddle implementation for "Cross-Lingual Word Embedding Refinement by โ„“1 Norm Optimisation" (NAACL 2021)

L1-Refinement Paddle implementation for "Cross-Lingual Word Embedding Refinement by โ„“1 Norm Optimisation" (NAACL 2021) ๐Ÿ™ˆ A more detailed readme is co

Lincedo Lab 4 Jun 09, 2021
An implementation of the paper "A Neural Algorithm of Artistic Style"

A Neural Algorithm of Artistic Style implementation - Neural Style Transfer This is an implementation of the research paper "A Neural Algorithm of Art

Srijarko Roy 27 Sep 20, 2022
Official code repository for ICCV 2021 paper: Gravity-Aware Monocular 3D Human Object Reconstruction

GraviCap Official code repository for ICCV 2021 paper: Gravity-Aware Monocular 3D Human Object Reconstruction. Gravity-Aware Monocular 3D Human-Object

Rishabh Dabral 15 Dec 09, 2022
It is a simple library to speed up CLIP inference up to 3x (K80 GPU)

CLIP-ONNX It is a simple library to speed up CLIP inference up to 3x (K80 GPU) Usage Install clip-onnx module and requirements first. Use this trick !

Gerasimov Maxim 93 Dec 20, 2022
From Canonical Correlation Analysis to Self-supervised Graph Neural Networks

Code for CCA-SSG model proposed in the NeurIPS 2021 paper From Canonical Correlation Analysis to Self-supervised Graph Neural Networks.

Hengrui Zhang 44 Nov 27, 2022
Discovering and Achieving Goals via World Models

Discovering and Achieving Goals via World Models [Project Website] [Benchmark Code] [Video (2min)] [Oral Talk (13min)] [Paper] Russell Mendonca*1, Ole

Oleg Rybkin 71 Dec 22, 2022
Does MAML Only Work via Feature Re-use? A Data Set Centric Perspective

Does-MAML-Only-Work-via-Feature-Re-use-A-Data-Set-Centric-Perspective Does MAML Only Work via Feature Re-use? A Data Set Centric Perspective Installin

2 Nov 07, 2022
This repository includes the official project for the paper: TransMix: Attend to Mix for Vision Transformers.

TransMix: Attend to Mix for Vision Transformers This repository includes the official project for the paper: TransMix: Attend to Mix for Vision Transf

Jie-Neng Chen 130 Jan 01, 2023
This repository contains python code necessary to replicated the experiments performed in our paper "Invariant Ancestry Search"

InvariantAncestrySearch This repository contains python code necessary to replicated the experiments performed in our paper "Invariant Ancestry Search

Phillip Bredahl Mogensen 0 Feb 02, 2022
This repository contains the accompanying code for Deep Virtual Markers for Articulated 3D Shapes, ICCV'21

Deep Virtual Markers This repository contains the accompanying code for Deep Virtual Markers for Articulated 3D Shapes, ICCV'21 Getting Started Get sa

KimHyomin 45 Oct 07, 2022
Code of the paper "Part Detector Discovery in Deep Convolutional Neural Networks" by Marcel Simon, Erik Rodner and Joachim Denzler

Part Detector Discovery This is the code used in our paper "Part Detector Discovery in Deep Convolutional Neural Networks" by Marcel Simon, Erik Rodne

Computer Vision Group Jena 17 Feb 22, 2022
Compressed Video Action Recognition

Compressed Video Action Recognition Chao-Yuan Wu, Manzil Zaheer, Hexiang Hu, R. Manmatha, Alexander J. Smola, Philipp Krรคhenbรผhl. In CVPR, 2018. [Proj

Chao-Yuan Wu 479 Dec 26, 2022
PyTorch implementation for OCT-GAN Neural ODE-based Conditional Tabular GANs (WWW 2021)

OCT-GAN: Neural ODE-based Conditional Tabular GANs (OCT-GAN) Code for reproducing the experiments in the paper: Jayoung Kim*, Jinsung Jeon*, Jaehoon L

BigDyL 7 Dec 27, 2022
Official implementation of the Neurips 2021 paper Searching Parameterized AP Loss for Object Detection.

Parameterized AP Loss By Chenxin Tao, Zizhang Li, Xizhou Zhu, Gao Huang, Yong Liu, Jifeng Dai This is the official implementation of the Neurips 2021

46 Jul 06, 2022
Visyerres sgdf woob - Modules Woob pour l'intranet et autres sites Scouts et Guides de France

Vis'Yerres SGDF - Modules Woob Vous avez le sentiment que l'intranet des Scouts

Thomas Touhey (pas un pseudonyme) 3 Dec 24, 2022
Python utility to generate filesystem content for Obsidian.

Security Vault Generator Quickly parse, format, and output common frameworks/content for Obsidian.md. There is a strong focus on MITRE ATT&CK because

Justin Angel 73 Dec 02, 2022
Object detection, 3D detection, and pose estimation using center point detection:

Objects as Points Object detection, 3D detection, and pose estimation using center point detection: Objects as Points, Xingyi Zhou, Dequan Wang, Phili

Xingyi Zhou 6.7k Jan 03, 2023
COVINS -- A Framework for Collaborative Visual-Inertial SLAM and Multi-Agent 3D Mapping

COVINS -- A Framework for Collaborative Visual-Inertial SLAM and Multi-Agent 3D Mapping Version 1.0 COVINS is an accurate, scalable, and versatile vis

ETHZ V4RL 183 Dec 27, 2022
DyStyle: Dynamic Neural Network for Multi-Attribute-Conditioned Style Editing

DyStyle: Dynamic Neural Network for Multi-Attribute-Conditioned Style Editing Figure: Joint multi-attribute edits using DyStyle model. Great diversity

74 Dec 03, 2022