All Projects → StacyYang → Msg Net

StacyYang / Msg Net

Multi-style Generative Network for Real-time Transfer

Programming Languages

lua
6591 projects

Projects that are alternatives of or similar to Msg Net

Pytorch Multi Style Transfer
Neural Style and MSG-Net
Stars: ✭ 687 (+351.97%)
Mutual labels:  deep-neural-networks, style-transfer, real-time
Zi2zi
Learning Chinese Character style with conditional GAN
Stars: ✭ 1,988 (+1207.89%)
Mutual labels:  deep-neural-networks, style-transfer
Caffe2 Ios
Caffe2 on iOS Real-time Demo. Test with Your Own Model and Photos.
Stars: ✭ 221 (+45.39%)
Mutual labels:  deep-neural-networks, real-time
favorite-research-papers
Listing my favorite research papers 📝 from different fields as I read them.
Stars: ✭ 12 (-92.11%)
Mutual labels:  style-transfer, generative-model
Vincent Ai Artist
Style transfer using deep convolutional neural nets
Stars: ✭ 176 (+15.79%)
Mutual labels:  generative-model, style-transfer
Segan
Speech Enhancement Generative Adversarial Network in TensorFlow
Stars: ✭ 661 (+334.87%)
Mutual labels:  deep-neural-networks, generative-model
mix-stage
Official Repository for the paper Style Transfer for Co-Speech Gesture Animation: A Multi-Speaker Conditional-Mixture Approach published in ECCV 2020 (https://arxiv.org/abs/2007.12553)
Stars: ✭ 22 (-85.53%)
Mutual labels:  style-transfer, generative-model
dreamsnap
Real life through the eyes of an artist
Stars: ✭ 16 (-89.47%)
Mutual labels:  real-time, style-transfer
Tracking With Darkflow
Real-time people Multitracker using YOLO v2 and deep_sort with tensorflow
Stars: ✭ 515 (+238.82%)
Mutual labels:  deep-neural-networks, real-time
Realtime object detection
Plug and Play Real-Time Object Detection App with Tensorflow and OpenCV. No Bugs No Worries. Enjoy!
Stars: ✭ 260 (+71.05%)
Mutual labels:  deep-neural-networks, real-time
Adain Style
Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization
Stars: ✭ 1,049 (+590.13%)
Mutual labels:  generative-model, style-transfer
Mxnet Gluon Style Transfer
Neural Style and MSG-Net
Stars: ✭ 105 (-30.92%)
Mutual labels:  style-transfer, real-time
Easy Neural Ode
Code for the paper "Learning Differential Equations that are Easy to Solve"
Stars: ✭ 146 (-3.95%)
Mutual labels:  deep-neural-networks
Avatar Net
Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decoration
Stars: ✭ 150 (-1.32%)
Mutual labels:  style-transfer
Djl
An Engine-Agnostic Deep Learning Framework in Java
Stars: ✭ 2,262 (+1388.16%)
Mutual labels:  deep-neural-networks
Optical Flow Filter
A real time optical flow algorithm implemented on GPU
Stars: ✭ 146 (-3.95%)
Mutual labels:  real-time
Webdnn
The Fastest DNN Running Framework on Web Browser
Stars: ✭ 1,850 (+1117.11%)
Mutual labels:  deep-neural-networks
Densenet Sdr
repo that holds code for improving on dropout using Stochastic Delta Rule
Stars: ✭ 148 (-2.63%)
Mutual labels:  deep-neural-networks
Pix2code
pix2code: Generating Code from a Graphical User Interface Screenshot
Stars: ✭ 11,349 (+7366.45%)
Mutual labels:  deep-neural-networks
Machine Learning Tutorials
machine learning and deep learning tutorials, articles and other resources
Stars: ✭ 11,692 (+7592.11%)
Mutual labels:  deep-neural-networks
Multi-style Generative Network for Real-time Transfer [arXiv] [project]
Hang Zhang, Kristin Dana
@article{zhang2017multistyle,
	title={Multi-style Generative Network for Real-time Transfer},
	author={Zhang, Hang and Dana, Kristin},
	journal={arXiv preprint arXiv:1703.06953},
	year={2017}
}

Installation

We also provide PyTorch implementation and MXNet implementation. Please install Torch7 with cuda and cudnn support. The code has been tested on Ubuntu 16.04 with Titan X Pascal and Maxwell.

luarocks install https://raw.githubusercontent.com/zhanghang1989/MSG-Net/master/texture-scm-1.rockspec

Test and Demo

  1. Clone the repo and download pre-trained models
    git clone [email protected]:zhanghang1989/MSG-Net.git
    cd MSG-Net/experiments
    bash models/download_models.sh 
    
  2. Web Camera Demo
    qlua webcam.lua
    
  3. Test on Image
    th test.lua -input_image images/content/venice-boat.jpg -image_size 1024
    eog stylized
    

[More Example Results]

Train Your Own Model

Please follow this tutorial to train a new model.

Release Timeline

  • [x] 03/20/2017 we have released the demo video.
  • [x] 03/24/2017 We have released ArXiv paper and test code with pre-trained models.
  • [x] 04/09/2017 We have released the training code.
  • [x] 04/24/2017 Please checkout our PyTorch implementation.

Acknowledgement

The code benefits from outstanding prior work and their implementations including:

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].