Data

Tools

Indexes

Applications

Experiments

Open Source Science

torchsr

Super Resolution datasets and models in Pytorch

https://github.com/coloquinte/torchsr

Science Score: 67.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ✓
    DOI references
    Found 5 DOI reference(s) in README
  • ✓
    Academic publication links
    Links to: arxiv.org, zenodo.org
  • ○
    Committers with academic emails
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (8.4%) to scientific vocabulary

Keywords

datasets edsr pytorch rcan rdn superresolution torchvision vdsr
Last synced: 6 months ago · JSON representation ·

Repository

Super Resolution datasets and models in Pytorch

Basic Info
  • Host: GitHub
  • Owner: Coloquinte
  • License: mit
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 445 KB
Statistics
  • Stars: 206
  • Watchers: 7
  • Forks: 21
  • Open Issues: 1
  • Releases: 5
Topics
datasets edsr pytorch rcan rdn superresolution torchvision vdsr
Created almost 5 years ago · Last pushed about 2 years ago
Metadata Files
Readme License Citation

README.md

DOI PyPI GitHub

Super-Resolution Networks for Pytorch

Super-resolution is a process that increases the resolution of an image, adding additional details. Methods using neural networks give the most accurate results, much better than other interpolation methods. With the right training, it is even possible to make photo-realistic images.

For example, here is a low-resolution image, magnified x4 by a neural network, and a high resolution image of the same object:

Pixelated image of a butterfly Smooth magnified image High resolution image

In this repository, you will find: * the popular super-resolution networks, pretrained * common super-resolution datasets * Pytorch datasets and transforms adapted to super-resolution * a unified training script for all models

Models

The following pretrained models are available. Click on the links for the paper: * EDSR * CARN * RDN * RCAN * NinaSR

Newer and larger models perform better: the most accurate models are EDSR (huge), RCAN and NinaSR-B2. For practical applications, I recommend a smaller model, such as NinaSR-B1.

Expand benchmark results
Set5 results | Network | Parameters (M) | 2x (PSNR/SSIM) | 3x (PSNR/SSIM) | 4x (PSNR/SSIM) | | ------------------- | -------------- | -------------- | -------------- | -------------- | | carn | 1.59 | 37.88 / 0.9600 | 34.32 / 0.9265 | 32.14 / 0.8942 | | carn\_m | 0.41 | 37.68 / 0.9594 | 34.06 / 0.9247 | 31.88 / 0.8907 | | edsr\_baseline | 1.37 | 37.98 / 0.9604 | 34.37 / 0.9270 | 32.09 / 0.8936 | | edsr | 40.7 | 38.19 / 0.9609 | 34.68 / 0.9293 | 32.48 / 0.8985 | | ninasr\_b0 | 0.10 | 37.72 / 0.9594 | 33.96 / 0.9234 | 31.77 / 0.8877 | | ninasr\_b1 | 1.02 | 38.14 / 0.9609 | 34.48 / 0.9277 | 32.28 / 0.8955 | | ninasr\_b2 | 10.0 | 38.21 / 0.9612 | 34.61 / 0.9288 | 32.45 / 0.8973 | | rcan | 15.4 | 38.27 / 0.9614 | 34.76 / 0.9299 | 32.64 / 0.9000 | | rdn | 22.1 | 38.12 / 0.9609 | 33.98 / 0.9234 | 32.35 / 0.8968 |
Set14 results | Network | Parameters (M) | 2x (PSNR/SSIM) | 3x (PSNR/SSIM) | 4x (PSNR/SSIM) | | ------------------- | -------------- | -------------- | -------------- | -------------- | | carn | 1.59 | 33.57 / 0.9173 | 30.30 / 0.8412 | 28.61 / 0.7806 | | carn\_m | 0.41 | 33.30 / 0.9151 | 30.10 / 0.8374 | 28.42 / 0.7764 | | edsr\_baseline | 1.37 | 33.57 / 0.9174 | 30.28 / 0.8414 | 28.58 / 0.7804 | | edsr | 40.7 | 33.95 / 0.9201 | 30.53 / 0.8464 | 28.81 / 0.7872 | | ninasr\_b0 | 0.10 | 33.24 / 0.9144 | 30.02 / 0.8355 | 28.28 / 0.7727 | | ninasr\_b1 | 1.02 | 33.71 / 0.9189 | 30.41 / 0.8437 | 28.71 / 0.7840 | | ninasr\_b2 | 10.0 | 34.00 / 0.9206 | 30.53 / 0.8461 | 28.80 / 0.7863 | | rcan | 15.4 | 34.13 / 0.9216 | 30.63 / 0.8475 | 28.85 / 0.7878 | | rdn | 22.1 | 33.71 / 0.9182 | 30.07 / 0.8373 | 28.72 / 0.7846 |
DIV2K results (validation set) | Network | Parameters (M) | 2x (PSNR/SSIM) | 3x (PSNR/SSIM) | 4x (PSNR/SSIM) | 8x (PSNR/SSIM) | | ------------------- | -------------- | -------------- | -------------- | -------------- | -------------- | | carn | 1.59 | 36.08 / 0.9451 | 32.37 / 0.8871 | 30.43 / 0.8366 | N/A | | carn\_m | 0.41 | 35.76 / 0.9429 | 32.09 / 0.8827 | 30.18 / 0.8313 | N/A | | edsr\_baseline | 1.37 | 36.13 / 0.9455 | 32.41 / 0.8878 | 30.43 / 0.8370 | N/A | | edsr | 40.7 | 36.56 / 0.9485 | 32.75 / 0.8933 | 30.73 / 0.8445 | N/A | | ninasr\_b0 | 0.10 | 35.77 / 0.9428 | 32.06 / 0.8818 | 30.09 / 0.8293 | 26.60 / 0.7084 | | ninasr\_b1 | 1.02 | 36.35 / 0.9471 | 32.51 / 0.8892 | 30.56 / 0.8405 | 26.96 / 0.7207 | | ninasr\_b2 | 10.0 | 36.52 / 0.9482 | 32.73 / 0.8926 | 30.73 / 0.8437 | 27.07 / 0.7246 | | rcan | 15.4 | 36.61 / 0.9489 | 32.78 / 0.8935 | 30.73 / 0.8447 | 27.17 / 0.7292 | | rdn | 22.1 | 36.32 / 0.9468 | 32.04 / 0.8822 | 30.61 / 0.8414 | N/A |
B100 results | Network | Parameters (M) | 2x (PSNR/SSIM) | 3x (PSNR/SSIM) | 4x (PSNR/SSIM) | | ------------------- | -------------- | -------------- | -------------- | -------------- | | carn | 1.59 | 32.12 / 0.8986 | 29.07 / 0.8042 | 27.58 / 0.7355 | | carn\_m | 0.41 | 31.97 / 0.8971 | 28.94 / 0.8010 | 27.45 / 0.7312 | | edsr\_baseline | 1.37 | 32.15 / 0.8993 | 29.08 / 0.8051 | 27.56 / 0.7354 | | edsr | 40.7 | 32.35 / 0.9019 | 29.26 / 0.8096 | 27.72 / 0.7419 | | ninasr\_b0 | 0.10 | 31.97 / 0.8974 | 28.90 / 0.8000 | 27.36 / 0.7290 | | ninasr\_b1 | 1.02 | 32.24 / 0.9004 | 29.13 / 0.8061 | 27.62 / 0.7377 | | ninasr\_b2 | 10.0 | 32.32 / 0.9014 | 29.23 / 0.8087 | 27.71 / 0.7407 | | rcan | 15.4 | 32.39 / 0.9024 | 29.30 / 0.8106 | 27.74 / 0.7429 | | rdn | 22.1 | 32.25 / 0.9006 | 28.90 / 0.8004 | 27.66 / 0.7388 |
Urban100 results | Network | Parameters (M) | 2x (PSNR/SSIM) | 3x (PSNR/SSIM) | 4x (PSNR/SSIM) | | ------------------- | -------------- | -------------- | -------------- | -------------- | | carn | 1.59 | 31.95 / 0.9263 | 28.07 / 0.849 | 26.07 / 0.78349 | | carn\_m | 0.41 | 31.30 / 0.9200 | 27.57 / 0.839 | 25.64 / 0.76961 | | edsr\_baseline | 1.37 | 31.98 / 0.9271 | 28.15 / 0.852 | 26.03 / 0.78424 | | edsr | 40.7 | 32.97 / 0.9358 | 28.81 / 0.865 | 26.65 / 0.80328 | | ninasr\_b0 | 0.10 | 31.33 / 0.9204 | 27.48 / 0.8374 | 25.45 / 0.7645 | | ninasr\_b1 | 1.02 | 32.48 / 0.9319 | 28.29 / 0.8555 | 26.25 / 0.7914 | | ninasr\_b2 | 10.0 | 32.91 / 0.9354 | 28.70 / 0.8640 | 26.54 / 0.8008 | | rcan | 15.4 | 33.19 / 0.9372 | 29.01 / 0.868 | 26.75 / 0.80624 | | rdn | 22.1 | 32.41 / 0.9310 | 27.49 / 0.838 | 26.36 / 0.79460 |

All models are defined in torchsr.models. Other useful tools to augment your models, such as self-ensemble methods and tiling, are present in torchsr.models.utils.

Datasets

The following datasets are available. Click on the links for the project page: * DIV2K * RealSR * Flicr2K * REDS * Set5, Set14, B100, Urban100

All datasets are defined in torchsr.datasets. They return a list of images, with the high-resolution image followed by downscaled or degraded versions. Data augmentation methods are provided in torchsr.transforms.

Datasets are downloaded automatically when using the download=True flag, or by running the corresponding script i.e. ./scripts/download_div2k.sh.

Usage

```python from torchsr.datasets import Div2K from torchsr.models import ninasrb0 from torchvision.transforms.functional import topilimage, totensor

Div2K dataset

dataset = Div2K(root="./data", scale=2, download=False)

Get the first image in the dataset (High-Res and Low-Res)

hr, lr = dataset[0]

Download a pretrained NinaSR model

model = ninasr_b0(scale=2, pretrained=True)

Run the Super-Resolution model

lrt = totensor(lr).unsqueeze(0) srt = model(lrt) sr = topilimage(sr_t.squeeze(0).clamp(0, 1)) sr.show() ```

Expand more examples ```python from torchsr.datasets import Div2K from torchsr.models import edsr, rcan from torchsr.models.utils import ChoppedModel, SelfEnsembleModel from torchsr.transforms import ColorJitter, Compose, RandomCrop # Div2K dataset, cropped to 256px, width color jitter dataset = Div2K( root="./data", scale=2, download=False, transform=Compose([ RandomCrop(256, scales=[1, 2]), ColorJitter(brightness=0.2) ])) # Pretrained RCAN model, with tiling for large images model = ChoppedModel( rcan(scale=2, pretrained=True), scale=2, chop_size=400, chop_overlap=10) # Pretrained EDSR model, with self-ensemble method for higher quality model = SelfEnsembleModel(edsr(scale=2, pretrained=True)) ```

Training

A script is available to train the models from scratch, evaluate them, and much more. It is not part of the pip package, and requires additional dependencies. More examples are available in scripts/.

bash pip install piq tqdm tensorboard # Additional dependencies python -m torchsr.train -h python -m torchsr.train --arch edsr_baseline --scale 2 --download-pretrained --images test/butterfly.png --destination results/ python -m torchsr.train --arch edsr_baseline --scale 2 --download-pretrained --validation-only python -m torchsr.train --arch edsr_baseline --scale 2 --epochs 300 --loss l1 --dataset-train div2k_bicubic

You can evaluate models from the command line as well. For example, for EDSR with the paper's PSNR evaluation: python -m torchsr.train --validation-only --arch edsr_baseline --scale 2 --dataset-val set5 --chop-size 400 --download-pretrained --shave-border 2 --eval-luminance

Acknowledgements

Thanks to the people behind torchvision and EDSR, whose work inspired this repository. Some of the models available here come from EDSR-PyTorch and CARN-PyTorch.

To cite this work, please use:

``` @misc{torchsr, author = {Gabriel Gouvine}, title = {Super-Resolution Networks for Pytorch}, year = {2021}, publisher = {GitHub}, journal = {GitHub repository}, howpublished = {\url{https://github.com/Coloquinte/torchSR}}, doi = {10.5281/zenodo.4868308} }

@misc{ninasr, author = {Gabriel Gouvine}, title = {NinaSR: Efficient Small and Large ConvNets for Super-Resolution}, year = {2021}, publisher = {GitHub}, journal = {GitHub repository}, howpublished = {\url{https://github.com/Coloquinte/torchSR/blob/main/doc/NinaSR.md}}, doi = {10.5281/zenodo.4868308} } ```

Owner

  • Name: Gabriel Gouvine
  • Login: Coloquinte
  • Kind: user
  • Location: Edinburgh
  • Company: AMD

Citation (CITATION.cff) 

cff-version: 1.2.0
title: torchSR
message: >-
  If you use this software and want to cite it, please use
  the citation below.
type: software
authors:
  - family-names: Gouvine
    given-names: Gabriel
    orcid: 0000-0003-3404-6659
repository-code: 'https://github.com/Coloquinte/torchSR'
keywords:
  - superresolution
  - pytorch
  - EDSR
  - RCAN
license: MIT
date-released: 2021-05-30
doi: 10.5281/zenodo.4868308

GitHub Events

Total
  • Watch event: 20
  • Fork event: 2
Last Year
  • Watch event: 20
  • Fork event: 2

Committers

Last synced: 9 months ago

All Time
  • Total Commits: 196
  • Total Committers: 3
  • Avg Commits per committer: 65.333
  • Development Distribution Score (DDS): 0.092
Past Year
  • Commits: 0
  • Committers: 0
  • Avg Commits per committer: 0.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
Gabriel Gouvine g****T@g****m 178
Gabriel Gouvine g****t@m****g 16
txfs19260817 d****5@g****m 2
Committer Domains (Top 20 + Academic)
m4x.org: 1 gmx.com: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time
  • Total issues: 12
  • Total pull requests: 1
  • Average time to close issues: 2 days
  • Average time to close pull requests: 1 day
  • Total issue authors: 9
  • Total pull request authors: 1
  • Average comments per issue: 2.25
  • Average comments per pull request: 1.0
  • Merged pull requests: 1
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • OwEnXiaoMing (3)
  • vishwa91 (2)
  • Fafa87 (1)
  • lchunleo (1)
  • sc-56 (1)
  • jcampbell05 (1)
  • FrancescoSaverioZuppichini (1)
  • wslgqq277g (1)
  • erjihaoshi (1)
Pull Request Authors
  • txfs19260817 (1)
Top Labels
Issue Labels
Pull Request Labels

Packages

  • Total packages: 1
  • Total downloads:
    • pypi 30,970 last-month
  • Total dependent packages: 0
  • Total dependent repositories: 1
  • Total versions: 3
  • Total maintainers: 1
pypi.org: torchsr

Super Resolution Networks for pytorch

  • Versions: 3
  • Dependent Packages: 0
  • Dependent Repositories: 1
  • Downloads: 30,970 Last month
Rankings
Downloads: 3.7%
Stargazers count: 6.1%
Forks count: 9.3%
Dependent packages count: 10.1%
Average: 10.2%
Dependent repos count: 21.6%
Maintainers (1)
coloquinte
Last synced: 6 months ago

Dependencies

setup.py pypi
  • torch >=1.6