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 → willylulu → Celeba Hq Modified

willylulu / Celeba Hq Modified

Licence: mit
Modified h5tool.py make user getting celeba-HQ easier

Programming Languages

python
139335 projects - #7 most used programming language

Labels

ganceleba

Projects that are alternatives of or similar to Celeba Hq Modified

Tensorflow DCGAN
Study Friendly Implementation of DCGAN in Tensorflow
Stars: ✭ 22 (-73.81%)
Mutual labels:  gan, celeba
Gan Tutorial
Simple Implementation of many GAN models with PyTorch.
Stars: ✭ 227 (+170.24%)
Mutual labels:  gan, celeba
Tf Exercise Gan
Tensorflow implementation of different GANs and their comparisions
Stars: ✭ 110 (+30.95%)
Mutual labels:  gan, celeba
Tf.gans Comparison
Implementations of (theoretical) generative adversarial networks and comparison without cherry-picking
Stars: ✭ 477 (+467.86%)
Mutual labels:  gan, celeba
Pycadl
Python package with source code from the course "Creative Applications of Deep Learning w/ TensorFlow"
Stars: ✭ 356 (+323.81%)
Mutual labels:  gan, celeba
DCGAN-CelebA-PyTorch-CPP
DCGAN Implementation using PyTorch in both C++ and Python
Stars: ✭ 14 (-83.33%)
Mutual labels:  gan, celeba
Msg Gan V1
MSG-GAN: Multi-Scale Gradients GAN (Architecture inspired from ProGAN but doesn't use layer-wise growing)
Stars: ✭ 116 (+38.1%)
Mutual labels:  gan, celeba
Alae
[CVPR2020] Adversarial Latent Autoencoders
Stars: ✭ 3,178 (+3683.33%)
Mutual labels:  gan, celeba
Pytorch Mnist Celeba Gan Dcgan
Pytorch implementation of Generative Adversarial Networks (GAN) and Deep Convolutional Generative Adversarial Networks (DCGAN) for MNIST and CelebA datasets
Stars: ✭ 363 (+332.14%)
Mutual labels:  gan, celeba
Began Tensorflow
Tensorflow implementation of "BEGAN: Boundary Equilibrium Generative Adversarial Networks"
Stars: ✭ 904 (+976.19%)
Mutual labels:  gan, celeba
Geneva
Code to train and evaluate the GeNeVA-GAN model for the GeNeVA task proposed in our ICCV 2019 paper "Tell, Draw, and Repeat: Generating and modifying images based on continual linguistic instruction"
Stars: ✭ 71 (-15.48%)
Mutual labels:  gan
Man
Multinomial Adversarial Networks for Multi-Domain Text Classification (NAACL 2018)
Stars: ✭ 72 (-14.29%)
Mutual labels:  gan
Semantic Object Accuracy For Generative Text To Image Synthesis
Code for "Semantic Object Accuracy for Generative Text-to-Image Synthesis" (TPAMI 2020)
Stars: ✭ 78 (-7.14%)
Mutual labels:  gan
Neuralnetworkpostprocessing
Unity Post Processing with Convolution Neural Network
Stars: ✭ 81 (-3.57%)
Mutual labels:  gan
Dcgan Tensorflow
A Tensorflow implementation of Deep Convolutional Generative Adversarial Networks trained on Fashion-MNIST, CIFAR-10, etc.
Stars: ✭ 70 (-16.67%)
Mutual labels:  gan
Artediting
Modeling Artistic Workflows for Image Generation and Editing (ECCV 2020)
Stars: ✭ 75 (-10.71%)
Mutual labels:  gan
Colorizer
Add colors to black and white images with neural networks (GANs).
Stars: ✭ 69 (-17.86%)
Mutual labels:  gan
Sequentialdata Gan
Tensorflow Implementation of GAN modeling for sequential data
Stars: ✭ 69 (-17.86%)
Mutual labels:  gan
Celebamask Hq
A large-scale face dataset for face parsing, recognition, generation and editing.
Stars: ✭ 1,156 (+1276.19%)
Mutual labels:  celeba
Dlcv for beginners
《深度学习与计算机视觉》配套代码
Stars: ✭ 1,244 (+1380.95%)
Mutual labels:  gan
View All Similar Projects ➔

celeba-hq-modified

imga

Changes I made (compared to original repo, see fork origin):

  • Added multithreading support for substantial speedup.
  • Save images using original filename (instead of index).

A modified approach to generate CelebA-HQ Dataset

The CelebA-HQ is a dataset introduced in Progressive Growing of GANs for Improved Quality (progressive_growing_of_gans), containing 30,000 high quality images from CelebA.

The images are originally stored as HDF5 format (.h5), which are not suitable for common data loaders. Therefore, I modified the h5tool.py to generate and save CelebA-HQ images in JPEG format (.jpg).

Usage

  1. Clone the original repository

git clone https://github.com/tkarras/progressive_growing_of_gans/tree/original-theano-version

  1. Clone this repository

git clone https://github.com/willylulu/celeb-hq-modified

  1. Replace h5tool.py in the original repo with the one in this repo

cp celeb-hq-modified/h5tool.py progressive_growing_of_gans/h5tool

  1. Create target directory in the original repository
cd progressive_growing_of_gans
mkdir celeba-hq
cd celeba-hq
mkdir celeba-64
mkdir celeba-128
mkdir celeba-256
mkdir celeba-512
mkdir celeba-1024
  1. Go back to home path

cd

  1. Create a directory B and download CelebA non-aligned version and put them in directory A

  2. Create a directory A and download CelebA-HQ zip file and put them in directory B

  3. Download annotation files and put them in directory B

  4. Execute h5tool.py python h5tool.py create_celeba_hq 123456.h5 <path to directory A> <path to directory B>

Reference

tkarras/progressive_growing_of_gans

CelebA

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].