Comments (5)
Thanks! Using the solution 1, the results are good!
from interfacegan.
How about setting --latent_space_type=w
, since you are using the boundary from W space.
from interfacegan.
Yes, I tried with --latent_space_type=w or --latent_space_type=W
but the outputs are not face anymore.
from interfacegan.
I use stylegan_ffhq to generate the images, and the generated images are great. Thus I think the model is correct.
from interfacegan.
That is because the current codebase will randomly sample w codes subject to Gaussian distribution instead of the actual distribution. There are basically two solutions
(1) Run generate_data.py
first, which will save w.npy
in the output folder. Then use -i
option in edit.py
to load the generated w codes.
(2) See HiGAN which provides a more robust generator, which will sample codes from the actual distribution.
from interfacegan.
Related Issues (20)
- AttributeError: module 'tensorflow' has no attribute 'get_variable' HOT 2
- Access to training modules
- how do I test on my own set of images? Whenever I try testing it opens up sample images..Any help will be appreciated, HOT 2
- How can we generate the 256 resolution images for style GAN on celebahq instead of 1024?
- Can I use my own face for Semantic Face Editing HOT 1
- changing dataset HOT 4
- Integrate expression boundaries
- What is the rationale behind sampling from the normal distribution for the W latent code, which is not a normal distribution at all?
- Training with custom dataset HOT 3
- vgg16_zhang_perceptual.pkl _pickle.UnpicklingError: invalid load key, '-'.
- pose attribute control
- how can i run an inference using CPU?
- how to get latent codes from jpg/png images? HOT 1
- question about the proof
- Can you provide me with ppgan_ celebahq.pth file as pre-training model HOT 1
- It can realize the attributes of other kinds of objects, not the search of face attributes, such as the conversion of landscape images into snow, rain, mountains, etc.
- Issue regarding method linear_interpolate in file utils/manipulator.py
- How to train a classifier to get attribute scores HOT 2
- does it provide the function of generating an eyeglass on my own face photo?
- About editing HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from interfacegan.