Comments (6)
If you check the paper you'll see that the model is trained to only change the facial expression without altering the background. To generate these images I do the following:
- Detect faces with the face_recognition library
- Crop the face and resize to 128x128
- Run it through the model
- Rescale the edited face to its original size and place it back into the image
from ganimation.
Hi,
For the moment we are not planning to release the trained model as we are working on future improvements. Everything is prepared to be easily trained with any dataset containing faces. The readme contains all the instructions.
from ganimation.
@albertpumarola Another question: test images are 128x128 face area. How did you put them back on the original image seamlessly like this :
from ganimation.
@leeeeeeo I have a same error as you mentioned first, how did you solve it?
from ganimation.
@voa18105 It's because the trained model is not public available. You need to train your own model to use the test code.
from ganimation.
@leeeeeeo yes, i see... now when i've specified the path to a model I've trained - the error is different
from ganimation.
Related Issues (20)
- Is this how you would run your sample images ? HOT 2
- TypeError: iteration over a 0-d array
- Problem with Preparing annotation
- Pretrained Openface HOT 3
- About the paper figure
- A question about some loss functions in the paper
- Give “Attention” a name.
- Suggestion of using AU R-CNN instead of OpenFace for better AU detection accuracy.
- tensors must have same number of dimensions: got 2 and 3
- Attention Loss
- TypeError: Cannot handle this data type HOT 1
- when training “the loss_d_real is negative value ” is OK? and why
- Generator is different from that in paper HOT 1
- AUs as input parameter for trained model HOT 1
- IndexError: During training 0-dim tensor error HOT 2
- Can you share you train data in this paper? HOT 1
- Pretrained Model HOT 2
- Demo??
- Why the c_dim is 5 HOT 1
- How to get tar_aus in the batch ,what is the tar_aus?
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 ganimation.