Read the paper about Latent Shift: https://arxiv.org/abs/2102.09475
Watch a video: https://www.youtube.com/watch?v=1fxSDP8DheI
Read the paper about Counterfactual Alignment: https://arxiv.org/abs/2312.02186
The main diagram:
| Smiling |
Arched Eyebrows |
|---|---|
 |
 |
| Mouth Slightly Open |
Young |
|---|---|
 |
 |
For a predicting of smiling
For a predicting of pointy_nose
$pip install latentshiftimport latentshift
# Load classifier and autoencoder
model = latentshift.classifiers.FaceAttribute(download=True)
ae = latentshift.autoencoders.VQGAN(weights="faceshq", download=True)
# Load image
input = torch.randn(1, 3, 1024, 1024)
# Defining Latent Shift module
attr = captum.attr.LatentShift(model, ae)
# Computes counterfactual for class 3.
output = attr.attribute(input, target=3)
