Open xwg0508 opened 1 year ago
Hi, since we train these 3 models separately, we generate the corresponding datasets with different configuration files. The provided amass.yaml is used to generate the dataset for our generative setup by default. To generate the dataset for our single-motion setup, set single_motion
to True
in the configuration file. To generate the dataset for the gmp setup, you need to set unified_orientation
to False
in the configuration file.
Hi Chengan, thank you very much for your amazing work and the open source!
I would like to ask a question. After running amass.py , I got three folders: train/val/test , they weren't be divided into generative/signle/gmp. So how to divide dataset into generative/signle/gmp?