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 → GlebSBrykin → SANET

GlebSBrykin / SANET

Licence: MIT license
Arbitrary Style Transfer with Style-Attentional Networks

Programming Languages

Jupyter Notebook
11667 projects
python
139335 projects - #7 most used programming language

Labels

style-transferattention-mechanismfast-neural-styleneural-art

Projects that are alternatives of or similar to SANET

MeuralPaint
TensorFlow implementation of CNN fast neural style transfer ⚡️ 🎨 🌌
Stars: ✭ 19 (-81.9%)
Mutual labels:  style-transfer, fast-neural-style
CycleGAN-Music-Style-Transfer-Refactorization
Symbolic Music Genre Transfer with CycleGAN - Refactorization
Stars: ✭ 28 (-73.33%)
Mutual labels:  style-transfer
VisualML
Interactive Visual Machine Learning Demos.
Stars: ✭ 104 (-0.95%)
Mutual labels:  style-transfer
zero-shot-style-transfer
TensorFlow Implementation of Several Zero-Shot Image Style Transfer Methods
Stars: ✭ 14 (-86.67%)
Mutual labels:  style-transfer
A-Persona-Based-Neural-Conversation-Model
No description or website provided.
Stars: ✭ 22 (-79.05%)
Mutual labels:  attention-mechanism
deep dream
DeepDream psychodelic image generator.
Stars: ✭ 39 (-62.86%)
Mutual labels:  style-transfer
AttentionGatedVNet3D
Attention Gated VNet3D Model for KiTS19——2019 Kidney Tumor Segmentation Challenge
Stars: ✭ 35 (-66.67%)
Mutual labels:  attention-mechanism
rudetoxifier
Code and data of "Methods for Detoxification of Texts for the Russian Language" paper
Stars: ✭ 30 (-71.43%)
Mutual labels:  style-transfer
ganslate
Simple and extensible GAN image-to-image translation framework. Supports natural and medical images.
Stars: ✭ 17 (-83.81%)
Mutual labels:  style-transfer
Android-Tensorflow-Style-Transfer
Based on tensorflow's style transfer Android project.
Stars: ✭ 18 (-82.86%)
Mutual labels:  style-transfer
3HAN
An original implementation of "3HAN: A Deep Neural Network for Fake News Detection" (ICONIP 2017)
Stars: ✭ 29 (-72.38%)
Mutual labels:  attention-mechanism
Shakespearizing-Modern-English
Code for "Jhamtani H.*, Gangal V.*, Hovy E. and Nyberg E. Shakespearizing Modern Language Using Copy-Enriched Sequence to Sequence Models" Workshop on Stylistic Variation, EMNLP 2017
Stars: ✭ 64 (-39.05%)
Mutual labels:  style-transfer
Multigrid-Neural-Architectures
Multigrid Neural Architecture
Stars: ✭ 28 (-73.33%)
Mutual labels:  attention-mechanism
Image recoloring
Image Recoloring Based on Object Color Distributions (Eurographics 2019)
Stars: ✭ 30 (-71.43%)
Mutual labels:  style-transfer
CartoonGAN-tensorflow
Simple code implement the paper of CartoonGAN(CVPR2018)
Stars: ✭ 14 (-86.67%)
Mutual labels:  style-transfer
linguistic-style-transfer-pytorch
Implementation of "Disentangled Representation Learning for Non-Parallel Text Style Transfer(ACL 2019)" in Pytorch
Stars: ✭ 55 (-47.62%)
Mutual labels:  style-transfer
domain-attention
codes for paper "Domain Attention Model for Multi-Domain Sentiment Classification"
Stars: ✭ 22 (-79.05%)
Mutual labels:  attention-mechanism
One-Shot-Voice-Cloning
☺️ One Shot Voice Cloning base on Unet-TTS
Stars: ✭ 118 (+12.38%)
Mutual labels:  style-transfer
halonet-pytorch
Implementation of the 😇 Attention layer from the paper, Scaling Local Self-Attention For Parameter Efficient Visual Backbones
Stars: ✭ 181 (+72.38%)
Mutual labels:  attention-mechanism
egfr-att
Drug effect prediction using neural network
Stars: ✭ 17 (-83.81%)
Mutual labels:  attention-mechanism
View All Similar Projects ➔

SANET

This is unofficial PyTorch implementation of "Arbitrary Style Transfer with Style-Attentional Networks".

Official paper: https://arxiv.org/abs/1812.02342v5

To run, download the weights and place them in the folder with Eval.py. Links to weights on Yandex.Disk:

Or, you can download the latest release. It contains all weights, codes and examples.

How to evaluate

To test the code, make changes to the following lines in the file Eval.py. here you need to specify the path to the image style and content. After that, save the changes to the file and run it.

parser.add_argument('--content', type=str, default = 'input/chicago.jpg',
                    help='File path to the content image')
parser.add_argument('--style', type=str, default = 'style/style11.jpg',
                    help='File path to the style image, or multiple style \
                    images separated by commas if you want to do style \
                    interpolation or spatial control')

How to train

You can train your own SANet using Train.ipynb

Examples

Original:

Content.jpg

Stylized under 1.jpg:

Content_stylized_1.jpg

Stylized under Composition-VII.jpg:

Content_stylized_Composition-VII.jpg

Stylized under Starry.jpg:

Content_stylized_Starry.jpg

Stylized under candy.jpg:

Content_stylized_candy.jpg

Stylized under la_muse.jpg:

Content_stylized_la_muse.jpg

Stylized under rain_princess.jpg:

Content_stylized_rain_princess.jpg

Stylized under seated_nude.jpg:

Content_stylized_seated_nude.jpg

Stylized under style11.jpg:

Content_stylized_style11.jpg

Stylized under udnie.jpg:

Content_stylized_udnie.jpg

Stylized under wave.jpg:

Content_stylized_wave.jpg

Stylized under wreck.jpg:

Content_stylized_wreck.jpg

Original:

chicago.jpg

Stylized under 1.jpg:

chicago_stylized_1.jpg

Stylized under Composition-VII.jpg:

chicago_stylized_Composition-VII.jpg

Stylized under Starry.jpg:

chicago_stylized_Starry.jpg

Stylized under candy.jpg:

chicago_stylized_candy.jpg

Stylized under la_muse.jpg:

chicago_stylized_la_muse.jpg

Stylized under rain_princess.jpg:

chicago_stylized_rain_princess.jpg

Stylized under seated_nude.jpg:

chicago_stylized_seated_nude.jpg

Stylized under style11.jpg:

chicago_stylized_style11.jpg

Stylized under udnie.jpg:

chicago_stylized_udnie.jpg

Stylized under wave.jpg:

chicago_stylized_wave.jpg

Stylized under wreck.jpg:

chicago_stylized_wreck.jpg

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].