Open TLi347 opened 2 years ago
It shouldn't affect the results. In pc_inpainter
we use masks to make sure the network does not have access to extra knowledge.
I find the img input is used in inpainting.Althougth the img input add noise,I think the img input can't be used in this place,the input img can't exist really. mask_data = masked_data_mean +torch.randn_like(x)*std[:,None,None,None]] .the mask_data_mean is equal to data(the img input) please correct me if my thoughts is error. sincerely
I find the img input is used in inpainting.Althougth the img input add noise,I think the img input can't be used in this place,the input img can't exist really. mask_data = masked_data_mean +torch.randn_like(x)*std[:,None,None,None]] .the mask_data_mean is equal to data(the img input) please correct me if my thoughts is error. sincerely
The next line of code masks out the information in mask_data
. As a result the inpainting algorithm does not know the ground truth.
Hi Yang Song,
In 30 row, section "Inpaint", Score SDE demo PyTorch.ipynb,
should it be changed to x = pc_inpainter(score_model, scaler(img*mask), mask) so that it wouldn't inference img from img?
Please correct me if I misunderstand this part.