Coder Social home page Coder Social logo

honlan / dmt Goto Github PK

View Code? Open in Web Editor NEW
117.0 7.0 20.0 46.31 MB

Disentangled Makeup Transfer with Generative Adversarial Network

Python 100.00%
makeup-transfer generative-adversarial-network disentangled-representations tensorflow computer-vision deep-learning

dmt's People

Contributors

honlan avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar

dmt's Issues

The train tricks

hello, thanks for this wonderful work, when i implement this project, i find the generated result is not good, so can you share some training tips, thanks!

Used to work fine, now only outputs black pixels

Hello,

I tried the code on colab a few weeks ago (only changing a few lines for compatibility), and it worked perfectly fine.
Now, it only outputs black images. The images have the correct dimensions, but they contain only black pixels.

Compatibility change in 'main.py':

# ~ import tensorflow as tf  # here
import tensorflow.compat.v1 as tf; tf.disable_v2_behavior()  # here
import numpy as np
from imageio import imread, imsave
import os, glob, cv2
imsave = cv2.imwrite  # and here

As I said, it worked after I made the changes, so these are not responsible for the strange behavior.
Would you have any idea?

Best regards.

De-make up problem

Hi,Honlan,i am appreciate it for your work,and i am trying to De-make up,How should i do it ?

Empty repo

Hi,

Thanks for the insightful research. I would like to reproduce your research but I cannot find the code?

Please advise

For fun, I implemented the frozen graph on Android

I know I'm shifting the RGB color values correctly but its still showing some yellow around the image which I can't explain. This is without optimizing; Only using X:0 and Y:0 as input and decoder_1/g:0 as output.

Screenshot_1563223674

Code not available

Hello,

Thank you very much for your research, it is very interesting. I would like to reproduce your research and reading the paper I though the code would be here, but I cannot seem to find it. Could you please point me in the right direction to find the code?

Thank you very much.

Lack of information

This repo is lack of information. For example, it doesn't have any installation guide for users to run. There's no describing what packages to be install

Training Codes

An excellent job!I’m really interested in your experiment,Could you provide your project codes for public available?Thanks a lot!

A question about DMT

Interesting work. Is DMT good for realtime processing in a phone? like many of those popular iphone apps doing similar things.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.