srgan - Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

  •        28

We run this script under TensorFlow 1.4 and the TensorLayer 1.8.0+. πŸš€ This repo will be moved to here (please star) for life-cycle management soon. More cool Computer Vision applications such as pose estimation and style transfer can be found in this organization.



Related Projects

Super-Resolution-using-Generative-Adversarial-Networks - An implementation of SRGAN model in Keras

  •    Python

This is an implementation of the SRGAN model proposed in the paper Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network in Keras. Note that this project is a work in progress. The SRGAN model is built in stages within Initially, only the SR-ResNet model is created, to which the VGG network is appended to create the pre-training model. The VGG weights are freezed as we will not update these weights.

tensorlayer - Deep Learning and Reinforcement Learning Library for Developers and Scientists

  •    Python

TensorLayer is a novel TensorFlow-based deep learning and reinforcement learning library designed for researchers and engineers. It provides a large collection of customizable neural layers / functions that are key to build real-world AI applications. TensorLayer is awarded the 2017 Best Open Source Software by the ACM Multimedia Society. Simplicity : TensorLayer lifts the low-level dataflow interface of TensorFlow to high-level layers / models. It is very easy to learn through the rich example codes contributed by a wide community.

tensorlayer-tricks - How to use TensorLayer


While research in Deep Learning continues to improve the world, we use a bunch of tricks to implement algorithms with TensorLayer day to day. Here are a summary of the tricks to use TensorLayer. If you find a trick that is particularly useful in practice, please open a Pull Request to add it to the document. If we find it to be reasonable and verified, we will merge it in.

cnn-models - ImageNet pre-trained models with batch normalization for the Caffe framework

  •    Python

This repository contains convolutional neural network (CNN) models trained on ImageNet by Marcel Simon at the Computer Vision Group Jena (CVGJ) using the Caffe framework as published in the accompanying technical report. Each model is in a separate subfolder and contains everything needed to reproduce the results. This repository focuses currently contains the batch-normalization-variants of AlexNet and VGG19 as well as the training code for Residual Networks (Resnet). No mean subtraction is required for the pre-trained models! We have a batch-normalization layer which basically does the same.

text-to-image - Generative Adversarial Text to Image Synthesis / Please Star -->

  •    Python

This is an experimental tensorflow implementation of synthesizing images. The images are synthesized using the GAN-CLS Algorithm from the paper Generative Adversarial Text-to-Image Synthesis. This implementation is built on top of the excellent DCGAN in Tensorflow. N.B You can downloads all data files needed manually or simply run the and put the correct files to the right directories.

deep-learning-book - γ€ŠDeep Learningγ€‹γ€Šζ·±εΊ¦ε­¦δΉ γ€‹ by Ian Goodfellow, Yoshua Bengio and Aaron Courville


This book was downloaded in HTML form and conviniently joined as a single PDF file for your enjoyment. PLEASE SUPPORT IAN GOODFELLOW and the authors if you can purchase the paper book at Amazon. It is not expensive ($72) and probably contains content that is newer and without typographic mistakes.

tensorflow-vgg16 - conversation of caffe vgg16 model to tensorflow

  •    Python

VGG-16 is my favorite image classification model to run because of its simplicity and accuracy. The creators of this model published a pre-trained binary that can be used in Caffe. This is to convert that specific file to a TensorFlow model and check its correctness.

Image-Super-Resolution - Implementation of Super Resolution CNN in Keras.

  •    Python

Implementation of Image Super Resolution CNN in Keras from the paper Image Super-Resolution Using Deep Convolutional Networks. Also contains models that outperforms the above mentioned model, termed Expanded Super Resolution, Denoiseing Auto Encoder SRCNN which outperforms both of the above models and Deep Denoise SR, which with certain limitations, outperforms all of the above.

DnCNN - Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising (TIP, 2017)

  •    Matlab

[demos] Demo_test_DnCNN-.m. [models] including the trained models for Gaussian denoising; a single model for Gaussian denoising, single image super-resolution (SISR) and deblocking.

Tensorflow-Tutorial - Tensorflow tutorial from basic to hard

  •    Python

In these tutorials, we will build our first Neural Network and try to build some advanced Neural Network architectures developed recent years. All methods mentioned below have their video and text tutorial in Chinese. Visit θŽ«ηƒ¦ Python for more.

TensorFlow-Tutorials - ν…μ„œν”Œλ‘œμš°λ₯Ό κΈ°μ΄ˆλΆ€ν„° μ‘μš©κΉŒμ§€ λ‹¨κ³„λ³„λ‘œ μ—°μŠ΅ν•  수 μžˆλŠ” μ†ŒμŠ€ μ½”λ“œλ₯Ό μ œκ³΅ν•©λ‹ˆλ‹€

  •    Python

ν…μ„œν”Œλ‘œμš°λ₯Ό κΈ°μ΄ˆλΆ€ν„° μ‘μš©κΉŒμ§€ λ‹¨κ³„λ³„λ‘œ μ—°μŠ΅ν•  수 μžˆλŠ” μ†ŒμŠ€ μ½”λ“œλ₯Ό μ œκ³΅ν•©λ‹ˆλ‹€. ν…μ„œν”Œλ‘œμš° 곡식 μ‚¬μ΄νŠΈμ—μ„œ μ œκ³΅ν•˜λŠ” μ•ˆλ‚΄μ„œμ˜ λŒ€λΆ€λΆ„μ˜ λ‚΄μš©μ„ 닀루고 있으며, 곡식 μ‚¬μ΄νŠΈμ—μ„œ μ œκ³΅ν•˜λŠ” μ†ŒμŠ€ μ½”λ“œλ³΄λ‹€λŠ” 훨씬 κ°„λž΅ν•˜κ²Œ μž‘μ„±ν•˜μ˜€μœΌλ―€λ‘œ μ‰½κ²Œ κ°œλ…μ„ 읡힐 수 μžˆμ„ 것 μž…λ‹ˆλ‹€. λ˜ν•œ, λͺ¨λ“  주석은 ν•œκΈ€λ‘œ(!) λ˜μ–΄ μžˆμŠ΅λ‹ˆλ‹€.

generative-models - Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.

  •    Python

Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow. Also present here are RBM and Helmholtz Machine. Generated samples will be stored in GAN/{gan_model}/out (or VAE/{vae_model}/out, etc) directory during training.

cnn-text-classification-tf-chinese - CNN for Chinese Text Classification in Tensorflow

  •    Python

This code belongs to the "Implementing a CNN for Text Classification in Tensorflow" blog post. It is slightly simplified implementation of Kim's Convolutional Neural Networks for Sentence Classification paper in Tensorflow.

cppn-gan-vae-tensorflow - Train CPPNs as a Generative Model, using Generative Adversarial Networks and Variational Autoencoder techniques to produce high resolution images

  •    Python

Train Compositional Pattern Producing Network as a Generative Model, using Generative Adversarial Networks and Variational Autoencoder techniques to produce high resolution images. Run python from the command line to train from scratch and experiment with different settings.

torchcv - TorchCV: a PyTorch vision library mimics ChainerCV

  •    Python

The accuracy of TorchCV SSD is ~1% lower than ChainerCV. This is because the VGG base model I use performs slightly worse. I did the experiment by replacing pytorch/vision VGG16 model with the model used in ChainerCV, the SSD512 model got 79.85% accuracy. FPNSSD512 is created by replacing SSD VGG16 network with FPN50, the rest is the same. It beats all SSD models. You can download the trained params here.

fast-neural-style-tensorflow - A tensorflow implementation for fast neural style!

  •    Python

A tensorflow implementation for Perceptual Losses for Real-Time Style Transfer and Super-Resolution. This code is based on Tensorflow-Slim and OlavHN/fast-neural-style.

We have large collection of open source products. Follow the tags from Tag Cloud >>

Open source products are scattered around the web. Please provide information about the open source projects you own / you use. Add Projects.