Bug related to choice of device (cpu or gpu)

[ajaarma]

Hi,
I am trying to run the example data (default provided with the package) with script run_interaction.py

The script was run on gpu.

At Line 58 it gave error:

gene_test, _ = GINN.model.encoder(x_test[idx].to(device));
Traceback (most recent call last):
File "", line 1, in
RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu)

However, when underlying device is CPUs, then code successfully ran.

Could you please fix it.

Thanks.

Regards
AJ