Tim Ho
### Expected results Will there be a Mask-X-RCNN structure for training in the future which is introduced in "Learning to Segment Everything"
Im wondering if ur using washed CASIA as training data. if yes, can u provide the washed list of CASIA? I can't find any valid link to download it. Thanks!
Do u know how to request for the CelebA Identity List? Will be glad if u have it!
Why did u only backward the GP instead of the entire D_cost=D_fake - D_real + gradient_penalty.
The link of washed up list for casia is dead. Can u upload a new one? Thanks!
its seems that the dimension is mismatched in class Mask(): `mask_weight --> cls+bbox -->dim = (4+1)*class_num x 256` `x = x.permute(0, 2, 3, 1) # dim = (B*rois.size()[0], 28, 28,...
1. Add "dagshub" option to the parameters setting in `setup` 2. Add two blog posts from dagshub to official-blog