The value of kl divergence is always 0

autonomousvision / occupancy_networks

This repository contains the code for the paper "Occupancy Networks - Learning 3D Reconstruction in Function Space"

https://avg.is.tuebingen.mpg.de/publications/occupancy-networks

MIT License

1.48k stars 291 forks source link

The value of kl divergence is always 0 #121

Open BJHYZJ opened 1 year ago

BJHYZJ commented 1 year ago

After I finished the training of onet, in the evaluation result, the value of kl divergence is always 0. I think this is because in the function infer_z, self.encoder_latent is always null. Is this reasonable?