def net_prediction(img, comask, fomask, model):
utils.prepare_data(img, comask, fomask)
normalize = transforms.Normalize(mean=saliency.mean, std=saliency.std)
transform = transforms.Compose([
transforms.ToTensor(),
normalize,
])
img, comask, cont, fomask = utils.test_data_loader(transform)
inputs = torch.cat((img, comask, cont, fomask), 0)
inputs = torch.unsqueeze(inputs, dim=0)
inputs = Variable(inputs.cuda(), volatile=True)
mask = model(inputs)
return mask
def net_prediction(img, mask, model):
if img.size != mask.size:
img = img.resize(mask.size)
utils.prepare_test_data(img, mask)
normalize = transforms.Normalize(mean=saliency.mean, std=saliency.std)
transform = transforms.Compose([transforms.ToTensor(), normalize, ])
img_ref, mask_ref = utils.test_data_loader(transform)
inputs = torch.cat((img_ref, mask_ref), 0)
inputs = torch.unsqueeze(inputs, dim=0)
inputs = Variable(inputs.cuda(), volatile=True)
feature = model(inputs)
# remove dimision 2,3
feature.squeeze_(dim=2)
feature.squeeze_(dim=2)
return feature