GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → aitorzip → Pytorch Srgan

aitorzip / Pytorch Srgan

Licence: gpl-3.0
A modern PyTorch implementation of SRGAN

Programming Languages

python
139335 projects - #7 most used programming language

Labels

deep-learningpytorchcomputer-visionconvolutional-neural-networkscnngangenerative-adversarial-networksuper-resolution

Projects that are alternatives of or similar to Pytorch Srgan

Iseebetter
iSeeBetter: Spatio-Temporal Video Super Resolution using Recurrent-Generative Back-Projection Networks | Python3 | PyTorch | GANs | CNNs | ResNets | RNNs | Published in Springer Journal of Computational Visual Media, September 2020, Tsinghua University Press
Stars: ✭ 202 (-30.1%)
Mutual labels:  convolutional-neural-networks, cnn, gan, generative-adversarial-network, super-resolution
Tensorflow Srgan
Tensorflow implementation of "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network" (Ledig et al. 2017)
Stars: ✭ 33 (-88.58%)
Mutual labels:  convolutional-neural-networks, gan, generative-adversarial-network, super-resolution
DLSS
Deep Learning Super Sampling with Deep Convolutional Generative Adversarial Networks.
Stars: ✭ 88 (-69.55%)
Mutual labels:  cnn, generative-adversarial-network, gan, super-resolution
Srgan
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Stars: ✭ 2,641 (+813.84%)
Mutual labels:  cnn, gan, super-resolution
Tensorflow Tutorial
Tensorflow tutorial from basic to hard, 莫烦Python 中文AI教学
Stars: ✭ 4,122 (+1326.3%)
Mutual labels:  cnn, gan, generative-adversarial-network
Srgan Tensorflow
Tensorflow implementation of the SRGAN algorithm for single image super-resolution
Stars: ✭ 754 (+160.9%)
Mutual labels:  cnn, generative-adversarial-network, super-resolution
Awesome Gan For Medical Imaging
Awesome GAN for Medical Imaging
Stars: ✭ 1,814 (+527.68%)
Mutual labels:  gan, generative-adversarial-network, super-resolution
Yann
This toolbox is support material for the book on CNN (http://www.convolution.network).
Stars: ✭ 41 (-85.81%)
Mutual labels:  convolutional-neural-networks, cnn, generative-adversarial-network
Jsi Gan
Official repository of JSI-GAN (Accepted at AAAI 2020).
Stars: ✭ 42 (-85.47%)
Mutual labels:  convolutional-neural-networks, generative-adversarial-network, super-resolution
Anime4k
A High-Quality Real Time Upscaler for Anime Video
Stars: ✭ 14,083 (+4773.01%)
Mutual labels:  convolutional-neural-networks, cnn, super-resolution
Exermote
Using Machine Learning to predict the type of exercise from movement data
Stars: ✭ 108 (-62.63%)
Mutual labels:  convolutional-neural-networks, gan, generative-adversarial-network
Deep Learning With Python
Deep learning codes and projects using Python
Stars: ✭ 195 (-32.53%)
Mutual labels:  convolutional-neural-networks, cnn, generative-adversarial-network
Fast Srgan
A Fast Deep Learning Model to Upsample Low Resolution Videos to High Resolution at 30fps
Stars: ✭ 417 (+44.29%)
Mutual labels:  cnn, generative-adversarial-network, super-resolution
Ranksrgan
ICCV 2019 (oral) RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolution. PyTorch implementation
Stars: ✭ 213 (-26.3%)
Mutual labels:  gan, generative-adversarial-network, super-resolution
Anime Face Gan Keras
A DCGAN to generate anime faces using custom mined dataset
Stars: ✭ 161 (-44.29%)
Mutual labels:  cnn, gan, generative-adversarial-network
A Pytorch Tutorial To Super Resolution
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network | a PyTorch Tutorial to Super-Resolution
Stars: ✭ 157 (-45.67%)
Mutual labels:  gan, generative-adversarial-network, super-resolution
Cyclegan Qp
Official PyTorch implementation of "Artist Style Transfer Via Quadratic Potential"
Stars: ✭ 59 (-79.58%)
Mutual labels:  convolutional-neural-networks, gan, generative-adversarial-network
Master Thesis Bayesiancnn
Master Thesis on Bayesian Convolutional Neural Network using Variational Inference
Stars: ✭ 222 (-23.18%)
Mutual labels:  convolutional-neural-networks, generative-adversarial-network, super-resolution
srgan
Pytorch implementation of "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network"
Stars: ✭ 39 (-86.51%)
Mutual labels:  generative-adversarial-network, gan, super-resolution
Makegirlsmoe web
Create Anime Characters with MakeGirlsMoe
Stars: ✭ 3,144 (+987.89%)
Mutual labels:  gan, generative-adversarial-network
View All Similar Projects ➔

PyTorch-SRGAN

A modern PyTorch implementation of SRGAN

It is deeply based on Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network paper published by the Twitter team (https://arxiv.org/abs/1609.04802) but I replaced activations by Swish (https://arxiv.org/abs/1710.05941)

You can start training out-of-the-box with the CIFAR-10 or CIFAR-100 datasets, to emulate the paper results however, you will need to download and clean the ImageNet dataset yourself. Results and weights are provided for the ImageNet dataset.

Contributions are welcome!

Requirements

Training

usage: train [-h] [--dataset DATASET] [--dataroot DATAROOT]
             [--workers WORKERS] [--batchSize BATCHSIZE]
             [--imageSize IMAGESIZE] [--upSampling UPSAMPLING]
             [--nEpochs NEPOCHS] [--generatorLR GENERATORLR]
             [--discriminatorLR DISCRIMINATORLR] [--cuda] [--nGPU NGPU]
             [--generatorWeights GENERATORWEIGHTS]
             [--discriminatorWeights DISCRIMINATORWEIGHTS] [--out OUT]

Example: ./train --cuda

This will start a training session in the GPU. First it will pre-train the generator using MSE error for 2 epochs, then it will train the full GAN (generator + discriminator) for 100 epochs, using content (mse + vgg) and adversarial loss. Although weights are already provided in the repository, this script will also generate them in the checkpoints file.

Testing

usage: test [-h] [--dataset DATASET] [--dataroot DATAROOT] [--workers WORKERS]
            [--batchSize BATCHSIZE] [--imageSize IMAGESIZE]
            [--upSampling UPSAMPLING] [--cuda] [--nGPU NGPU]
            [--generatorWeights GENERATORWEIGHTS]
            [--discriminatorWeights DISCRIMINATORWEIGHTS]

Example: ./test --cuda

This will start a testing session in the GPU. It will display mean error values and save the generated images in the output directory, all three versions: low resolution, high resolution (original) and high resolution (generated).

Results

Training

The following results have been obtained with the current training setup:

  • Dataset: 350K randomly selected ImageNet samples
  • Input image size: 24x24
  • Output image size: 96x96 (16x)

Other training parameters are the default of train script

Tensorboard training graphs

Testing

Testing has been executed on 128 randomly selected ImageNet samples (disjoint from training set)

[7/8] Discriminator_Loss: 1.4123 Generator_Loss (Content/Advers/Total): 0.0901/0.6152/0.0908

Examples

See more under the output directory

High resolution / Low resolution / Recovered High Resolution

Original doggy Low res doggy Generated doggy

Original woman Low res woman Generated woman

Original hair Low res hair Generated hair

Original sand Low res sand Generated sand

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].