PyTorch implementation of neural style randomization for data augmentation

Related tags

Deep Learning style-augmentation
Overview

README

Augment training images for deep neural networks by randomizing their visual style, as described in our paper: https://arxiv.org/abs/1809.05375

To the best of our knowledge, this is also the only PyTorch implementation (with trained weights) of the arbitrary style transfer network in "Exploring the structure of a real-time, arbitrary neural artistic stylization network": https://arxiv.org/abs/1705.06830

Installation

python setup.py install

Usage example

from styleaug import StyleAugmentor

import torch
from torchvision.transforms import ToTensor, ToPILImage
from PIL import Image
import matplotlib.pyplot as plt


# PyTorch Tensor <-> PIL Image transforms:
toTensor = ToTensor()
toPIL = ToPILImage()

# load image:
im = Image.open('mug.png')
im_torch = toTensor(im).unsqueeze(0) # 1 x 3 x 256 x 256
im_torch = im_torch.to('cuda:0' if torch.cuda.is_available() else 'cpu')

# create style augmentor:
augmentor = StyleAugmentor()

# randomize style:
im_restyled = augmentor(im_torch)

# display:
plt.imshow(toPIL(im_restyled.squeeze().cpu()))
plt.show()

Cite

Please cite our paper if you use this code in your own work:

@inproceedings{jackson2019style,
  title={Style Augmentation: Data Augmentation via Style Randomization},
  author={Jackson, Philip T and Atapour-Abarghouei, Amir and Bonner, Stephen and Breckon, Toby P and Obara, Boguslaw},
  booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops},
  pages={83--92},
  year={2019}
}
You might also like...
PyTorch implementation of paper: AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer, ICCV 2021.
PyTorch implementation of paper: AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer, ICCV 2021.

AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer [Paper] [PyTorch Implementation] [Paddle Implementation] Overview This reposit

null 148 Dec 30, 2022
pytorch implementation of fast-neural-style
pytorch implementation of fast-neural-style

fast-neural-style 🌇 🚀 NOTICE: This codebase is no longer maintained, please use the codebase from pytorch examples repository available at pytorch/e

Abhishek Kadian 405 Dec 15, 2022
Implementation of Neural Style Transfer in Pytorch

PytorchNeuralStyleTransfer Code to run Neural Style Transfer from our paper Image Style Transfer Using Convolutional Neural Networks. Also includes co

Leon Gatys 396 Dec 1, 2022
Team nan solution repository for FPT data-centric competition. Data augmentation, Albumentation, Mosaic, Visualization, KNN application
Team nan solution repository for FPT data-centric competition. Data augmentation, Albumentation, Mosaic, Visualization, KNN application

FPT_data_centric_competition - Team nan solution repository for FPT data-centric competition. Data augmentation, Albumentation, Mosaic, Visualization, KNN application

Pham Viet Hoang (Harry) 2 Oct 30, 2022
Pytorch codes for
Pytorch codes for "Self-supervised Multi-view Stereo via Effective Co-Segmentation and Data-Augmentation"

Self-Supervised-MVS This repository is the official PyTorch implementation of our AAAI 2021 paper: "Self-supervised Multi-view Stereo via Effective Co

hongbin_xu 127 Jan 4, 2023
State-of-the-art data augmentation search algorithms in PyTorch
State-of-the-art data augmentation search algorithms in PyTorch

MuarAugment Description MuarAugment is a package providing the easiest way to a state-of-the-art data augmentation pipeline. How to use You can instal

null 43 Dec 12, 2022
Neural style transfer in PyTorch.
Neural style transfer in PyTorch.

style-transfer-pytorch An implementation of neural style transfer (A Neural Algorithm of Artistic Style) in PyTorch, supporting CPUs and Nvidia GPUs.

Katherine Crowson 395 Jan 6, 2023
Neural style transfer as a class in PyTorch

pt-styletransfer Neural style transfer as a class in PyTorch Based on: https://github.com/alexis-jacq/Pytorch-Tutorials Adds: StyleTransferNet as a cl

Tyler Kvochick 31 Jun 27, 2022
Pytorch tutorials for Neural Style transfert

PyTorch Tutorials This tutorial is no longer maintained. Please use the official version: https://pytorch.org/tutorials/advanced/neural_style_tutorial

Alexis David Jacq 135 Jun 26, 2022
Comments
  • Would like to know how to augment two image with the same style?

    Would like to know how to augment two image with the same style?

    Many thanks for your library on style augmentation which boost my imagination. I am thinking about using this augmentation on dual-camera setup. I guess it may be better if I stylized two images in the same way, but don't know how to do it? I would like to know the recommended way of controlling this ramdomness in this library

    opened by Owen-Liuyuxuan 3
  • How can I stylize from a specific style image?

    How can I stylize from a specific style image?

    I use get_embedding_mean_and_covariance.py to generate embedding. And change line 'im_restyled = augmentor(im_torch)' to 'im_restyled = augmentor(im_torch, alpha=alpha, embedding=embedding)', but seems not work. All the style images get the same result. Could weights in 'styleaug/checkpoints/checkpoint_stylepredictor.pth' is not right?

    opened by xuduo35 2
  • GPU out of memory

    GPU out of memory

    Hi,

    Thanks for the nice work, I tested run some small images and the preliminary results looks great!

    But I was trying to apply inferencing on large image 8k x 8k with provided weight resulting in some GPU memory issue: (my maximum GPU ram for each core is 32 GB) RuntimeError: CUDA out of memory. Tried to allocate 1.49 GiB (GPU 1; 31.75 GiB total capacity; 29.74 GiB already allocated; 673.75 MiB free; 29.77 GiB reserved in total by PyTorch)

    Do you have some suggestions on how to resolve it ?

    opened by Xiaoyang-Rebecca 0
  • Shouldn't be StylePredictor and Transfer Network trained jointly ?

    Shouldn't be StylePredictor and Transfer Network trained jointly ?

    Hi,

    Thanks for your work and sharing your code ! Here in the Style Predictor code you say you detach the embedding vector because you don't want to train "end-to-end".

    In the original paper from Ghiasi et al., they explicitely say : "We find it sufficient to jointly train the style prediction network P(·) and style transfer network T(·) on a large corpus of photographs and paintings"

    How can the Style Predictor net be trained then with your implementation ?

    opened by virgile-blg 2
Owner
null
GitHub
Transfer style api - An API to use with Tranfer Style App, where you can use two image and transfer the style

Transfer Style API It's an API to use with Tranfer Style App, where you can use

Brian Alejandro 1 Feb 13, 2022
The source code for the Cutoff data augmentation approach proposed in this paper: "A Simple but Tough-to-Beat Data Augmentation Approach for Natural Language Understanding and Generation".

Cutoff: A Simple Data Augmentation Approach for Natural Language This repository contains source code necessary to reproduce the results presented in

Dinghan Shen 49 Dec 22, 2022
Image transformations designed for Scene Text Recognition (STR) data augmentation. Published at ICCV 2021 Workshop on Interactive Labeling and Data Augmentation for Vision.

Data Augmentation for Scene Text Recognition (ICCV 2021 Workshop) (Pronounced as "strog") Paper Arxiv Why it matters? Scene Text Recognition (STR) req

Rowel Atienza 152 Dec 28, 2022
Fast Neural Style for Image Style Transform by Pytorch

FastNeuralStyle by Pytorch Fast Neural Style for Image Style Transform by Pytorch This is famous Fast Neural Style of Paper Perceptual Losses for Real

Bengxy 81 Sep 3, 2022
Pytorch implementation of Cut-Thumbnail in the paper Cut-Thumbnail:A Novel Data Augmentation for Convolutional Neural Network.

Cut-Thumbnail (Accepted at ACM MULTIMEDIA 2021) Tianshu Xie, Xuan Cheng, Xiaomin Wang, Minghui Liu, Jiali Deng, Tao Zhou, Ming Liu This is the officia

null 3 Apr 12, 2022
Only a Matter of Style: Age Transformation Using a Style-Based Regression Model

Only a Matter of Style: Age Transformation Using a Style-Based Regression Model The task of age transformation illustrates the change of an individual

null 444 Dec 30, 2022
Official PyTorch implementation of the ICRA 2021 paper: Adversarial Differentiable Data Augmentation for Autonomous Systems.

Adversarial Differentiable Data Augmentation This repository provides the official PyTorch implementation of the ICRA 2021 paper: Adversarial Differen

Manli 3 Oct 15, 2022
SpecAugmentPyTorch - A Pytorch (support batch and channel) implementation of GoogleBrain's SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition

SpecAugment An implementation of SpecAugment for Pytorch How to use Install pytorch, version>=1.9.0 (new feature (torch.Tensor.take_along_dim) is used

IMLHF 3 Oct 11, 2022
PyTorch implementation of neural style transfer algorithm

neural-style-pt This is a PyTorch implementation of the paper A Neural Algorithm of Artistic Style by Leon A. Gatys, Alexander S. Ecker, and Matthias

null 770 Jan 2, 2023
Official PyTorch implementation of "ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows"

ArtFlow Official PyTorch implementation of the paper: ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows Jie An*, Siyu Huang*, Yibing

null 123 Dec 27, 2022