Trained model is not public? about ganimation HOT 6 CLOSED

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:

1. Detect faces with the face_recognition library
2. Crop the face and resize to 128x128
3. Run it through the model
4. 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.