Shikhar Dev Gupta
Shikhar Dev Gupta
Depends on the model you want to use. The PSPNet101 trained on Cityscapes requires about 9.6GB memory, while the smaller PSPNet50 trained on ADE20K requires only about 3 GB.
Was this problem ever resolved? I am facing the same issue as @lorinczb
Hi guys!! Does anyone know if the sample_rate in hparams.py need to be changed to the sampling frequency of the sound files in the dataset? Like 16K for the Nancy...
Did you explore this any further? I am inclined towards going this way as well..