nv-tlabs / ATISS

Code for "ATISS: Autoregressive Transformers for Indoor Scene Synthesis", NeurIPS 2021
Other
264 stars 55 forks source link

The KL divergence #43

Closed WWalter-Lee closed 9 months ago

WWalter-Lee commented 9 months ago

In the script evaluate_kl_divergence_object_category.py, the code for selecting the data is as follows:

parser.add_argument( "--splits", choices=[ "training", "validation" ], default="training", help="Split to evaluate" )

The choice is limited to the training set and validation set, whereas the test set needs to be selected during the evaluation process. Considering the calculated values, using the training set yields values mentioned in the paper, which are < 0.01. In contrast, when using the test data, the KL values are > 0.01, the difference in values is approximately 5 to 10 times.