A simple PyTorch Implementation of Generative Adversarial Networks, focusing on anime face drawing.

AnimeGAN

A simple PyTorch Implementation of Generative Adversarial Networks, focusing on anime face drawing.

Randomly Generated Images

The images are generated from a DCGAN model trained on 143,000 anime character faces for 100 epochs.

fake_sample_1

Image Interpolation

Manipulating latent codes, enables the transition from images in the first row to the last row.

transition

Original Images

The images are not clean, some outliers can be observed, which degrades the quality of the generated images.

real_sample

Usage

To run the experiment,

$ python main.py --dataRoot path_to_dataset/ 

The pretrained model for DCGAN are also in this repo, play it inside the jupyter notebook.

anime-faces Dataset

Anime-style images of 126 tags are collected from danbooru.donmai.us using the crawler tool gallery-dl. The images are then processed by a anime face detector python-animeface. The resulting dataset contains ~143,000 anime faces. Note that some of the tags may no longer meaningful after cropping, i.e. the cropped face images under 'uniform' tag may not contain visible parts of uniforms.

How to construct the dataset from scratch ?

Prequisites: gallery-dl, python-animeface

  1. Download anime-style images

    # download 1000 images under the tag "misaka_mikoto"
    gallery-dl --images 1000 "https://danbooru.donmai.us/posts?tags=misaka_mikoto"
    
    # in a multi-processing manner
    cat tags.txt | \
    xargs -n 1 -P 12 -I 'tag' \ 
    bash -c ' gallery-dl --images 1000 "https://danbooru.donmai.us/posts?tags=$tag" '
  2. Extract faces from the downloaded images

    import animeface
    from PIL import Image
    
    im = Image.open('images/anime_image_misaka_mikoto.png')
    faces = animeface.detect(im)
    x,y,w,h = faces[0].face.pos
    im = im.crop((x,y,x+w,y+h))
    im.show() # display

I've cleaned the original dataset, the new version of the dataset has 115085 images in 126 tags. You can access the images from:

Non-commercial use please.

Things I've learned

  1. GANs are really hard to train.
  2. DCGAN generally works well, simply add fully-connected layers causes problems.
  3. In my cases, more layers for G yields better images, in the sense that G should be more powerful than D.
  4. Add noise to D's inputs and labels helps stablize training.
  5. Use differnet input and generate resolution (64x64 vs 96x96), there seems no obvious difference during training, the generated images are also very similar.
  6. Binray Noise as G's input amazingly works, but the images are not as good as those with Gussian Noise, idea credit to @cwhy ['Binary Noise' here I mean a sequence of {-1,1} generated by bernoulli distribution at p=0.5 ]

I did not carefully verify them, if you are looking for some general GAN tips, see @soumith's ganhacks

Others

  1. This project is heavily influenced by chainer-DCGAN and IllustrationGAN, the codes are mostly borrowed from PyTorch DCGAN example, thanks the authors for the clean codes.
  2. Dependencies: pytorch, torchvision
  3. This is a toy project for me to learn PyTorch and GANs, most importantly, for fun! :) Any feedback is welcome.

@jayleicn

Owner
Jie Lei 雷杰
UNC CS PhD student, vision+language.
Jie Lei 雷杰
Comments
  • KeyError: 'module name can\'t contain

    KeyError: 'module name can\'t contain "."'

    The classes in module.py contains some nn.Module layers whose names contains some'.' in it, so I got error messages like the title, so how could I play it??

  • no image under some tags

    no image under some tags

    Hi, The dataset from google drive contains 126 tags. However, some folders are emtpy:

    1girl apron blush collarbone hairclip honma_meiko japanese_clothes monochrome necktie nishizumi_miho purple_eyes scarf school_uniform sunglasses

    Is this normal? Thanks

  • set_sizes_contiguous is not allowed on a Tensor created from .data or .detach().

    set_sizes_contiguous is not allowed on a Tensor created from .data or .detach().

    input.data.resize_(real_cpu.size()).copy_(real_cpu) RuntimeError: set_sizes_contiguous is not allowed on a Tensor created from .data or .detach(). If your intent is to change the metadata of a Tensor (such as sizes / strides / storage / storage_offset) without autograd tracking the change, remove the .data / .detach() call and wrap the change in a with torch.no_grad(): block. For example, change: x.data.set_(y) to: with torch.no_grad(): x.set_(y)

  • can not run

    can not run

    Traceback (most recent call last): File "main.py", line 6, in import torch File "/Library/Python/2.7/site-packages/torch/init.py", line 81, in from torch._C import * RuntimeError: module compiled against API version 0xa but this version of numpy is 0x9

  • How do I start with my own model

    How do I start with my own model

    I would like to know how I can use this image generation to generate my own images from a self made model?

    Where can I read upon on this. I find no concrete info on making the models.

A highly efficient, fast, powerful and light-weight anime downloader and streamer for your favorite anime.
A highly efficient, fast, powerful and light-weight anime downloader and streamer for your favorite anime.

AnimDL - Download & Stream Your Favorite Anime AnimDL is an incredibly powerful tool for downloading and streaming anime. Core features Abuses the dev

Dec 2, 2022
Little tool in python to watch anime from the terminal (the better way to watch anime)

ani-cli Script working again :), thanks to the fork by Dink4n for the alternative approach to by pass the captcha on gogoanime A cli to browse and wat

Nov 28, 2022
SSD: Single Shot MultiBox Detector pytorch implementation focusing on simplicity
SSD: Single Shot MultiBox Detector pytorch implementation focusing on simplicity

SSD: Single Shot MultiBox Detector Introduction Here is my pytorch implementation of 2 models: SSD-Resnet50 and SSDLite-MobilenetV2.

Dec 3, 2022
Implementation for Paper "Inverting Generative Adversarial Renderer for Face Reconstruction"

StyleGAR TODO: add arxiv link Implementation of Inverting Generative Adversarial Renderer for Face Reconstruction TODO: for test Currently, some model

Oct 27, 2022
Minimal PyTorch implementation of Generative Latent Optimization from the paper "Optimizing the Latent Space of Generative Networks"
Minimal PyTorch implementation of Generative Latent Optimization from the paper

Minimal PyTorch implementation of Generative Latent Optimization This is a reimplementation of the paper Piotr Bojanowski, Armand Joulin, David Lopez-

Nov 27, 2022
Unofficial implementation of Alias-Free Generative Adversarial Networks. (https://arxiv.org/abs/2106.12423) in PyTorch
Unofficial implementation of Alias-Free Generative Adversarial Networks. (https://arxiv.org/abs/2106.12423) in PyTorch

alias-free-gan-pytorch Unofficial implementation of Alias-Free Generative Adversarial Networks. (https://arxiv.org/abs/2106.12423) This implementation

Nov 26, 2022
Pytorch implementation for reproducing StackGAN_v2 results in the paper StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks
Pytorch implementation for reproducing StackGAN_v2 results in the paper StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks

StackGAN-v2 StackGAN-v1: Tensorflow implementation StackGAN-v1: Pytorch implementation Inception score evaluation Pytorch implementation for reproduci

Nov 29, 2022
PyTorch implementation of "Learning to Discover Cross-Domain Relations with Generative Adversarial Networks"
PyTorch implementation of

DiscoGAN in PyTorch PyTorch implementation of Learning to Discover Cross-Domain Relations with Generative Adversarial Networks. * All samples in READM

Nov 27, 2022
Alias-Free Generative Adversarial Networks (StyleGAN3) Official PyTorch implementation
Alias-Free Generative Adversarial Networks (StyleGAN3) Official PyTorch implementation

Alias-Free Generative Adversarial Networks (StyleGAN3) Official PyTorch implementation

Nov 28, 2022
Digan - Official PyTorch implementation of Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks
Digan - Official PyTorch implementation of Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks

DIGAN (ICLR 2022) Official PyTorch implementation of "Generating Videos with Dyn

Nov 25, 2022
A Kernel fuzzer focusing on race bugs

Razzer: Finding kernel race bugs through fuzzing Environment setup $ source scripts/envsetup.sh scripts/envsetup.sh sets up necessary environment var

Nov 27, 2022
Simulation of self-focusing of laser beams in condensed media
Simulation of self-focusing of laser beams in condensed media

What is it? Program for scientific research, which allows to simulate the phenomenon of self-focusing of different laser beams (including Gaussian, ri

Jun 2, 2022
StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.
StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.

StudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditional image generation.

Dec 2, 2022
PyTorch implementations of Generative Adversarial Networks.
PyTorch implementations of Generative Adversarial Networks.

This repository has gone stale as I unfortunately do not have the time to maintain it anymore. If you would like to continue the development of it as

Nov 28, 2022
Variational autoencoder for anime face reconstruction
Variational autoencoder for anime face reconstruction

VAE animeface Variational autoencoder for anime face reconstruction Introduction This repository is an exploratory example to train a variational auto

Dec 11, 2021
Partial implementation of ODE-GAN technique from the paper Training Generative Adversarial Networks by Solving Ordinary Differential Equations
Partial implementation of ODE-GAN technique from the paper Training Generative Adversarial Networks by Solving Ordinary Differential Equations

ODE GAN (Prototype) in PyTorch Partial implementation of ODE-GAN technique from the paper Training Generative Adversarial Networks by Solving Ordinary

Feb 10, 2022
Official implementation of "Learning to Discover Cross-Domain Relations with Generative Adversarial Networks"
Official implementation of

DiscoGAN Official PyTorch implementation of Learning to Discover Cross-Domain Relations with Generative Adversarial Networks. Prerequisites Python 2.7

Nov 23, 2022
[TIP 2021] SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction
[TIP 2021] SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction

SADRNet Paper link: SADRNet: Self-Aligned Dual Face Regression Networks for Robust 3D Dense Face Alignment and Reconstruction Requirements python

Nov 23, 2022