Official implementation of "SinIR: Efficient General Image Manipulation with Single Image Reconstruction" (ICML 2021)

Related tags

Deep LearningSinIR
Overview

SinIR (Official Implementation)

Requirements

To install requirements:

pip install -r requirements.txt

We used Python 3.7.4 and f-strings which are introduced in python 3.6+

Training

To train a model, write a proper yaml config file in 'config_train' folder (sample yaml files provided in the config_train folder), and run this command:

python train.py <gpu_num> -y <yaml_file_in_'config_train'_folder>

For example, if you want to train a model with config_train/photo.yaml on gpu 0, run:

python train.py 0 -y photo

This will output a trained model, training logs, training output images and so on, to a subdirectory of 'outs' folder with proper naming and numbering which are used for inference.

Note that even though we provide one yaml file for each task, they can be used interchangeably, except few tasks.

You can copy and modify them depending on your purpose. Detailed explanation about configuration is written in the sample yaml files. Please read through it carefully if you need.

Inference

To carry out inference (i.e., image manipulation), you can specify inference yaml files in training yaml files. Please see provided sample training yaml files.

Or alternatively you can run this command:

python infer.py <output_dirnum> <gpu_num> -y <yaml_file_in_config_folder>

For example, if you want to carry out inference with a trained model numbered 002, with config_infer/photo_infer.yaml on gpu 0, run:

python infer.py 2 0 -y photo_infer

Then it will automatically find an output folder numbered 002 and conduct image manipulation, saving related results in the subdirectory.

Note that duplicated numbering (which can be avoided with a normal usage) will incur error. In this case, please keep only one output folder.

We also provide sample yaml files for inference which are paired with yaml files for training. Feel free to copy and modify depending on your purpose.

Acknowledgement

This repository includes images from:

  1. https://www2.eecs.berkeley.edu/Research/Projects/CS/vision/bsds/ (BSD dataset)
  2. https://github.com/luanfujun/deep-painterly-harmonization/ (https://arxiv.org/abs/1804.03189)
  3. https://github.com/luanfujun/deep-photo-styletransfer (https://arxiv.org/abs/1703.07511)
  4. The Web (free images)

This repository includes codes snippets from:

  1. SSIM: https://github.com/VainF/pytorch-msssim
  2. Anti-aliasing + Bicubic resampling: https://github.com/thstkdgus35/bicubic_pytorch
  3. dilated mask: https://github.com/tamarott/SinGAN
Align and Prompt: Video-and-Language Pre-training with Entity Prompts

ALPRO Align and Prompt: Video-and-Language Pre-training with Entity Prompts [Paper] Dongxu Li, Junnan Li, Hongdong Li, Juan Carlos Niebles, Steven C.H

Salesforce 127 Dec 21, 2022
Really awesome semantic segmentation

really-awesome-semantic-segmentation A list of all papers on Semantic Segmentation and the datasets they use. This site is maintained by Holger Caesar

Holger Caesar 400 Nov 28, 2022
General Assembly Capstone: NBA Game Predictor

Project 6: Predicting NBA Games Problem Statement Can I predict the results of NBA games from the back-half of a season from the opening half of the s

Adam Muhammad Klesc 1 Jan 14, 2022
9th place solution

AllDataAreExt-Galixir-Kaggle-HPA-2021-Solution Team Members Qishen Ha is Master of Engineering from the University of Tokyo. Machine Learning Engineer

daishu 5 Nov 18, 2021
PySOT - SenseTime Research platform for single object tracking, implementing algorithms like SiamRPN and SiamMask.

PySOT is a software system designed by SenseTime Video Intelligence Research team. It implements state-of-the-art single object tracking algorit

STVIR 4.1k Dec 29, 2022
functorch is a prototype of JAX-like composable function transforms for PyTorch.

functorch is a prototype of JAX-like composable function transforms for PyTorch.

Facebook Research 1.2k Jan 09, 2023
A Simulation Environment to train Robots in Large Realistic Interactive Scenes

iGibson: A Simulation Environment to train Robots in Large Realistic Interactive Scenes iGibson is a simulation environment providing fast visual rend

Stanford Vision and Learning Lab 493 Jan 04, 2023
SafePicking: Learning Safe Object Extraction via Object-Level Mapping, ICRA 2022

SafePicking Learning Safe Object Extraction via Object-Level Mapping Kentaro Wad

Kentaro Wada 49 Oct 24, 2022
StorSeismic: An approach to pre-train a neural network to store seismic data features

StorSeismic: An approach to pre-train a neural network to store seismic data features This repository contains codes and resources to reproduce experi

Seismic Wave Analysis Group 11 Dec 05, 2022
TransGAN: Two Transformers Can Make One Strong GAN

[Preprint] "TransGAN: Two Transformers Can Make One Strong GAN", Yifan Jiang, Shiyu Chang, Zhangyang Wang

VITA 1.5k Jan 07, 2023
This is the official implementation for the paper "Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalization" in NeurIPS 2021.

MPMAB_BEACON This is code used for the paper "Decentralized Multi-player Multi-armed Bandits: Beyond Linear Reward Functions", Neurips 2021. Requireme

Cong Shen Research Group 0 Oct 26, 2021
Using BERT+Bi-LSTM+CRF

Chinese Medical Entity Recognition Based on BERT+Bi-LSTM+CRF Step 1 I share the dataset on my google drive, please download the whole 'CCKS_2019_Task1

Xiang WU 55 Dec 21, 2022
An open-source Deep Learning Engine for Healthcare that aims to treat & prevent major diseases

AlphaCare Background AlphaCare is a work-in-progress, open-source Deep Learning Engine for Healthcare that aims to treat and prevent major diseases. T

Siraj Raval 44 Nov 05, 2022
A PyTorch implementation of the Relational Graph Convolutional Network (RGCN).

Torch-RGCN Torch-RGCN is a PyTorch implementation of the RGCN, originally proposed by Schlichtkrull et al. in Modeling Relational Data with Graph Conv

Thiviyan Singam 66 Nov 30, 2022
PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners for self-supervised ViT.

MAE for Self-supervised ViT Introduction This is an unofficial PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners for self-sup

36 Oct 30, 2022
A pytorch implementation of Pytorch-Sketch-RNN

Pytorch-Sketch-RNN A pytorch implementation of https://arxiv.org/abs/1704.03477 In order to draw other things than cats, you will find more drawing da

Alexis David Jacq 172 Dec 12, 2022
Python implementation of Project Fluent

Project Fluent This is a collection of Python packages to use the Fluent localization system. python-fluent consists of these packages: fluent.syntax

Project Fluent 155 Dec 28, 2022
[Preprint] "Bag of Tricks for Training Deeper Graph Neural Networks A Comprehensive Benchmark Study" by Tianlong Chen*, Kaixiong Zhou*, Keyu Duan, Wenqing Zheng, Peihao Wang, Xia Hu, Zhangyang Wang

Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study Codes for [Preprint] Bag of Tricks for Training Deeper Graph

VITA 101 Dec 29, 2022
Prediction of MBA refinance Index (Mortgage prepayment)

Prediction of MBA refinance Index (Mortgage prepayment) Deep Neural Network based Model The ability to predict mortgage prepayment is of critical use

Ruchil Barya 1 Jan 16, 2022
Unoffical reMarkable AddOn for Firefox.

reMarkable for Firefox (Download) This repo converts the offical reMarkable Chrome Extension into a Firefox AddOn published here under the name "Unoff

Jelle Schutter 45 Nov 28, 2022