All Projects → kayr7 → PyTorch-SRGAN

kayr7 / PyTorch-SRGAN

Licence: Apache-2.0 License
PyTorch version of the paper: "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network"

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to PyTorch-SRGAN

Srgan
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Stars: ✭ 2,641 (+18764.29%)
Mutual labels:  vgg19, srgan
mSRGAN-A-GAN-for-single-image-super-resolution-on-high-content-screening-microscopy-images.
Generative Adversarial Network for single image super-resolution in high content screening microscopy images
Stars: ✭ 52 (+271.43%)
Mutual labels:  vgg19, srgan
SRGAN-Keras-Implementation
Photo Realistic Single Image Super-Resolution Using a Generative Adversarial Network implemented in Keras
Stars: ✭ 25 (+78.57%)
Mutual labels:  srgan
SRGAN-PyTorch
An Unofficial PyTorch Implementation for Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Stars: ✭ 52 (+271.43%)
Mutual labels:  srgan
Keras-MultiClass-Image-Classification
Multiclass image classification using Convolutional Neural Network
Stars: ✭ 48 (+242.86%)
Mutual labels:  vgg19
PhotographicImageSynthesiswithCascadedRefinementNetworks-Pytorch
Photographic Image Synthesis with Cascaded Refinement Networks - Pytorch Implementation
Stars: ✭ 63 (+350%)
Mutual labels:  vgg19
vgg-caffe
The VGG16 and VGG19 networks in caffe with jupyter notebook
Stars: ✭ 45 (+221.43%)
Mutual labels:  vgg19
caffe srgan
A Caffe Implementation of SRGAN
Stars: ✭ 59 (+321.43%)
Mutual labels:  srgan
Image-Classification
Pre-trained VGG-Net Model for image classification using tensorflow
Stars: ✭ 29 (+107.14%)
Mutual labels:  vgg19
neural-style-pytorch
Neural Style implementation in PyTorch! 🎨
Stars: ✭ 50 (+257.14%)
Mutual labels:  vgg19
CIFAR10-VGG19-Tensorflow
No description or website provided.
Stars: ✭ 27 (+92.86%)
Mutual labels:  vgg19
Basicsr
Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also support StyleGAN2, DFDNet.
Stars: ✭ 2,708 (+19242.86%)
Mutual labels:  srgan
SRGAN-PyTorch
A PyTorch implementation of SRGAN specific for Anime Super Resolution based on "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network". And another PyTorch WGAN-gp implementation of SRGAN referring to "Improved Training of Wasserstein GANs".
Stars: ✭ 65 (+364.29%)
Mutual labels:  srgan

PyTorch-SRGAN

Source: SRResNetVgg5,4: (Ground Truth: )

PyTorch version of the paper: Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (currently it does not implement the GAN, but the srresnet + vgg19-5,4 loss)

you can train a net from scratch: (optionally start training with just the pixel-wise loss on the resnet part: python srresnet.py --image-dir traindir --cuda --pretraining --images 16384 --batchSize 16)

(use --pretrained modelfile.pth to continue from a pretraining or previous run for example) python srresnet.py --image-dir traindir --cuda --images 16384 --batchSize 16

and then inference with the arguments: --pretrained model/model_epoch_80.pth --testing --test-image BSDS300/images/train/100075.jpg

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].