The issue on the evaluation of VQVAE

[LinghaoChan]

Dear authors,

I found that the evaluation of VQVAE includes a line of codes (here):

if args.resume_pth : 
    logger.info('loading checkpoint from {}'.format(args.resume_pth))
    ckpt = torch.load(args.resume_pth, map_location='cpu')
    net.load_state_dict(ckpt['net'], strict=True)
net.train()
net.cuda()

why does the evaluation use train() not eval()?

Best

[Jiro-zhang]

We set net.eval() in the test function, so net.train() will not affect the evaluation.

T2M-GPT/utils/eval_trans.py

Line 22 in 7db71a2

net.eval()

[LinghaoChan]

Okay. got it! Many thanks!❤️