How to use MAISI's VAE encoder to encode a CT?

[paproaskwar]

Really appreciate your wonderful job!!!

Here is my code when I use AutoencoderKlMaisi to encode a CT:

The code looks good, but when I save the latent(z_mu) as a .nii file and displayed in 3D Slicer, the latent looks pretty noisy.
is that normal?

autoencoder = define_instance(args, "autoencoder_def").to(device)
checkpoint_autoencoder = torch.load(args.trained_autoencoder_path, weights_only=True)
autoencoder.load_state_dict(checkpoint_autoencoder)
autoencoder.eval()

with torch.no_grad(), torch.cuda.amp.autocast():
     z_mu, z_sigma = autoencoder.encode(images)

[Can-Zhao]

Yes