PerceptualLoss uses memory on GPU 0 when specified otherwise

[FeliMe]

When running PerceptualLoss on a machine with multiple GPUs, it always uses some memory of GPU 0, even when gpu_ids specifies another one.

Minimal example to reproduce:

import models
from time import sleep

model = models.PerceptualLoss(model='net-lin', net='vgg', gpu_ids=[2])
sleep(20)

[richzhang]

Hi, perhaps a quick fix is to do export CUDA_VISIBLE_DEVICES=2 on the command lind