The official code of Anisotropic Stroke Control for Multiple Artists Style Transfer

Last update: Nov 21, 2022

Related tags

Deep Learning ASMAGAN

Overview

ASMA-GAN

Anisotropic Stroke Control for Multiple Artists Style Transfer

Proceedings of the 28th ACM International Conference on Multimedia

The official repository with Pytorch

[Arxiv paper]

Methodology

Dependencies

python3.6+
pytorch1.5+
torchvision
pyyaml
paramiko
pandas
requests
tensorboard
tensorboardX
tqdm

Installation

We highly recommend you to use Anaconda for installation

conda create -n ASMA python=3.6
conda activate ASMA
conda install pytorch==1.5.0 torchvision==0.6.0 cudatoolkit=10.1 -c pytorch
pip install pyyaml paramiko pandas requests tensorboard tensorboardX tqdm

Preparation

Traning dataset
- Coming soon
pre-trained model
- Download the model from Github Releases, and unzip the files to ./train_logs/

Usage

To test with pretrained model

The command line below will generate 1088*1920 HD style migration pictures of 11 painters for each picture of testImgRoot (11 painters include: Berthe Moriso , Edvard Munch, Ernst Ludwig Kirchner, Jackson Pollock, Wassily Kandinsky, Oscar-Claude Monet, Nicholas Roerich, Paul Cézanne, Pablo Picasso ,Samuel Colman, Vincent Willem van Gogh. The output image(s) can be found in ./test_logs/ASMAfinal/

Example of style transfer with all 11 artists style

python main.py --mode test --cuda 0 --version ASMAfinal  --dataloader_workers 8   --testImgRoot ./bench/ --nodeName localhost --checkpoint 350000 --testScriptsName common_useage --specify_sytle -1

Example of style transfer with Pablo Picasso style

python main.py --mode test --cuda 0 --version ASMAfinal  --dataloader_workers 8   --testImgRoot ./bench/ --nodeName localhost --checkpoint 350000 --testScriptsName common_useage --specify_sytle 8

Example of style transfer with Wassily Kandinsky style

python main.py --mode test --cuda 0 --version ASMAfinal  --dataloader_workers 8   --testImgRoot ./bench/ --nodeName localhost --checkpoint 350000 --testScriptsName common_useage --specify_sytle 4

--version refers to the ASMAGAN training logs name.

--testImgRoot can be a folder with images or the path of a single picture.You can assign the image(s) you want to perform style transfer to this argument.

--specify_sytle is used to specify which painter's style is used for style transfer. When the value is -1, 11 painters' styles are used for image(s) respectively for style transfer. The values corresponding to each painter's style are as follows [0: Berthe Moriso, 1: Edvard Munch, 2: Ernst Ludwig Kirchner, 3: Jackson Pollock, 4: Wassily Kandinsky, 5: Oscar-Claude Monet, 6: Nicholas Roerich, 7: Paul Cézanne, 8: Pablo Picasso, 9 : Samuel Colman, 10: Vincent Willem van Gogh]

Training

Coming soon

To cite our paper

@inproceedings{DBLP:conf/mm/ChenYLQN20,
  author    = {Xuanhong Chen and
               Xirui Yan and
               Naiyuan Liu and
               Ting Qiu and
               Bingbing Ni},
  title     = {Anisotropic Stroke Control for Multiple Artists Style Transfer},
  booktitle = {{MM} '20: The 28th {ACM} International Conference on Multimedia, 2020},
  publisher = {{ACM}},
  year      = {2020},
  url       = {https://doi.org/10.1145/3394171.3413770},
  doi       = {10.1145/3394171.3413770},
  timestamp = {Thu, 15 Oct 2020 16:32:08 +0200},
  biburl    = {https://dblp.org/rec/conf/mm/ChenYLQN20.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

Some Results

Related Projects

Learn about our other projects [RainNet], [Sketch Generation], [CooGAN], [Knowledge Style Transfer], [SimSwap],[ASMA-GAN],[Pretrained_VGG19].

High Resolution Results

Comments

Can't download pre-trained model

Hi! Could you please check your pre-trained model. The follow links is no found. Thank you https://github.com/neuralchen/ASMAGAN/releases/download/v.1.0/ASMAfinal.zip

opened by namdn 5
Thank you for your great project. When will the training code be released
Thank you for your great project.

When will the training code be released.

I want to get more painters how do I do that, how do I make the training datasets, how much data do I need

Looking forward to your reply
opened by zhanghongyong123456 5
Fine Tuning for single class

Hello team, I would like to finetune your pretrained model for just five new class (total output will be five), how should I use the finetune? Thank you!

opened by minhtcai 0
KeyError 1920

using the official command: python main.py --mode test --cuda 0 --version ASMAfinal --dataloader_workers 8 --testImgRoot ./bench/ --nodeName localhost --checkpoint 350000 --testScriptsName common_useage --specify_sytle 8

then error happened Generator Script Name: Conditional_Generator_asm 11 classes Finished preprocessing the test dataset, total image number: 25... /home/ama/anaconda3/envs/ASMA/lib/python3.9/site-packages/torchvision/transforms/transforms.py:332: UserWarning: Argument interpolation should be of type InterpolationMode instead of int. Please, use InterpolationMode enum. warnings.warn( Traceback (most recent call last): File "/home/ama/ASMAGAN/main.py", line 266, in tester.test() File "/home/ama/ASMAGAN/test_scripts/tester_common_useage.py", line 50, in test test_data = TestDataset(test_img,batch_size) File "/home/ama/ASMAGAN/data_tools/test_data_loader_resize.py", line 36, in init transform.append(T.Resize(1088,1920)) File "/home/ama/anaconda3/envs/ASMA/lib/python3.9/site-packages/torchvision/transforms/transforms.py", line 336, in init interpolation = _interpolation_modes_from_int(interpolation) File "/home/ama/anaconda3/envs/ASMA/lib/python3.9/site-packages/torchvision/transforms/functional.py", line 47, in _interpolation_modes_from_int return inverse_modes_mapping[i] KeyError: 1920

opened by Kayce001 1
Change aspect ratio of images

test code change aspect ratio of input images so output images are deformed to fix this i make some correction at "test_data_loader_resize.py"

opened by birolkuyumcu 0
RuntimeError: cuDNN

Hi I get the following error when running the code:

RuntimeError: cuDNN error: CUDNN_STATUS_EXECUTION_FAILED when calling backward()

I would appreciate your help on how to resolve this.

Thank you!

Gero

opened by Limbicnation 8

Releases(v.1.1)

v.1.1(Jun 14, 2021)

ASMA pretrained model
Source code(tar.gz)
Source code(zip)
ASMAfinal.zip(194.71 MB)
data_art_backup.zip(1427.14 MB)

Owner

Six_God

GitHub Repository

git《Investigating Loss Functions for Extreme Super-Resolution》(CVPR 2020) GitHub:

Investigating Loss Functions for Extreme Super-Resolution NTIRE 2020 Perceptual Extreme Super-Resolution Submission. Our method ranked first and secon

0 Oct 17, 2022

Pocsploit is a lightweight, flexible and novel open source poc verification framework

208 Dec 24, 2022

This is a repository of our model for weakly-supervised video dense anticipation.

Introduction This is a repository of our model for weakly-supervised video dense anticipation. More results on GTEA, Epic-Kitchens etc. will come soon

2 Apr 09, 2022

[SIGGRAPH Asia 2021] Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGAN

Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGAN [Paper] [Project Website] [Output resutls] Official Pytorch i

215 Dec 17, 2022

AI Face Mesh: This is a simple face mesh detection program based on Artificial intelligence.

AI Face Mesh: This is a simple face mesh detection program based on Artificial Intelligence which made with Python. It's able to detect 468 different

1 Jan 13, 2022

From Canonical Correlation Analysis to Self-supervised Graph Neural Networks

Code for CCA-SSG model proposed in the NeurIPS 2021 paper From Canonical Correlation Analysis to Self-supervised Graph Neural Networks.

44 Nov 27, 2022

CLIP+FFT text-to-image

Aphantasia This is a text-to-image tool, part of the artwork of the same name. Based on CLIP model, with FFT parameterizer from Lucent library as a ge

690 Jan 02, 2023

This code is an implementation for Singing TTS.

MLP Singer This code is an implementation for Singing TTS. The algorithm is based on the following papers: Tae, J., Kim, H., & Lee, Y. (2021). MLP Sin

22 Dec 23, 2022

Py-faster-rcnn - Faster R-CNN (Python implementation)

py-faster-rcnn has been deprecated. Please see Detectron, which includes an implementation of Mask R-CNN. Disclaimer The official Faster R-CNN code (w

7.8k Jan 03, 2023

Urban mobility simulations with Python3, RLlib (Deep Reinforcement Learning) and Mesa (Agent-based modeling)

Deep Reinforcement Learning for Smart Cities Documentation RLlib: https://docs.ray.io/en/master/rllib.html Mesa: https://mesa.readthedocs.io/en/stable

1 May 15, 2022

Implementation of PersonaGPT Dialog Model

PersonaGPT An open-domain conversational agent with many personalities PersonaGPT is an open-domain conversational agent cpable of decoding personaliz

42 Jan 01, 2023

A PaddlePaddle implementation of Time Interval Aware Self-Attentive Sequential Recommendation.

TiSASRec.paddle A PaddlePaddle implementation of Time Interval Aware Self-Attentive Sequential Recommendation. Introduction 论文：Time Interval Aware Sel

2 Nov 28, 2021

A hifiasm fork for metagenome assembly using Hifi reads.

hifiasm_meta - de novo metagenome assembler, based on hifiasm, a haplotype-resolved de novo assembler for PacBio Hifi reads.

44 Jul 10, 2022

Rotation-Only Bundle Adjustment

ROBA: Rotation-Only Bundle Adjustment Paper, Video, Poster, Presentation, Supplementary Material In this repository, we provide the implementation of

51 Nov 29, 2022

Discovering Explanatory Sentences in Legal Case Decisions Using Pre-trained Language Models.

Statutory Interpretation Data Set This repository contains the data set created for the following research papers: Savelka, Jaromir, and Kevin D. Ashl

17 Dec 23, 2022

Official Implementation for Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation

Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation We present a generic image-to-image translation framework, pixel2style2pixel (pSp

2.8k Dec 30, 2022

PAMI stands for PAttern MIning. It constitutes several pattern mining algorithms to discover interesting patterns in transactional/temporal/spatiotemporal databases

Introduction PAMI stands for PAttern MIning. It constitutes several pattern mining algorithms to discover interesting patterns in transactional/tempor

43 Jan 08, 2023