yhlleo / uaggan Goto Github PK

Hi,
I have gotten the following error during the test phase?
File "test.py", line 47, in
model = create_model(opt) # create a model given opt.model and other options
File "/media/deep/DATA/New_CODE/working3/amena/uaggan/models/init.py", line 65, in create_model
instance = model(opt)
File "/media/deep/DATA/New_CODE/working3/amena/uaggan/models/uag_gan_model.py", line 27, in init
BaseModel.init(self, opt)
File "/media/deep/DATA/New_CODE/working3/amena/uaggan/models/base_model.py", line 35, in init
self.device = torch.device('cuda:{}'.format(self.gpu_ids[0])) if self.gpu_ids else torch.device('cpu') # get device name: CPU or GPU
AttributeError: module 'torch' has no attribute 'device'

Hi,
Thank you for this task. If I want to make attention in the background that I need to change rather than the object. For example, in domain A and B, we have horse images, when translating from domain A - B, I want to keep the same horse in domain B but the background will be changed as domain A. How I can do that? Thank you in advance.

Could you pls explain the insights behind adding early stop training? Why we need to stop the gradient of attention networks?

In paper, authors have mentioned that they have not used mask till 30 epochs for D. Also, they have not trained attention portion after 30 epochs. Have you used these conditions in codes?