error occured when run on windows cpu

[zhangyunming]

hi, because there is no GPU on my windows pc, so i change the GPU to cpu by :

and chang the code in imagematting/inference.py line 98: , _, matte = modnet(im.cpu(), inference=False)

but error occured as:

my torch-cpu=1.6.0 thanks.

[ZHKKKe]

Hi. Thanks for your attention.

Our pre-trained models are wrapped by nn.DataParallel. For your problem, you may need to load the ckpt file by using:

model.load_state_dict(torch.load(args.ckpt_path, map_location=torch.device('cpu'))['module'])

Thank you for pointing it out. We will soon improve the code to make it compatible with cpu.

[zhangyunming]

###for cpu
modnet = MODNet(backbone_pretrained=False)
modnet = nn.DataParallel(modnet)
modnet.load_state_dict(torch.load(args.ckpt_path,map_location=torch.device('cpu')))
modnet.eval()

just ok above.  i delete  modnet = nn.DataParallel(modnet).
thanks

[ZHKKKe]

Yes. This is another solution. Good job :)