James-Andrew R. Sarmiento

Results 92 comments of James-Andrew R. Sarmiento

Yes On Mon, Aug 1, 2022, 17:37 Tianheng Cheng ***@***.***> wrote: > Hi @sarmientoj24 , thanks for your > interest in SparseInst. > Have you load any pretrained weights? >...

Hi, I am having a problem dealing with a multi-class task where dimensions are like these: ``` MASK TARGET: torch.Size([4, 1, 600, 900, 3]) OUTPUT: torch.Size([4, 5, 600, 900] ```...

@kuprel how do i access each image individually if I use the command line?

is there a way to disable that warning?

How different is the Generator structure from the `stylegan2-pytorch` or `stylegan2-pytorch-ada`?

But the NVLabs SG2 has this `SynthesisNetwork` and `MappingNetwork` which can be seen [here](https://github.com/NVlabs/stylegan2-ada-pytorch/blob/6f160b3d22b8b178ebe533a50d4d5e63aedba21d/training/networks.py#L493) ``` self.synthesis = SynthesisNetwork(w_dim=w_dim, img_resolution=img_resolution, img_channels=img_channels, **synthesis_kwargs) self.num_ws = self.synthesis.num_ws self.mapping = MappingNetwork(z_dim=z_dim, c_dim=c_dim, w_dim=w_dim, num_ws=self.num_ws,...

Can you advise me how do I convert the Generator part from your code to the NVLabs one?

I have already matched the MappingNetwork albeit it took me some time. On the SynthesisNetwork, I can see this `affine` FC layer [here](https://github.com/NVlabs/stylegan2-ada-pytorch/blob/6f160b3d22b8b178ebe533a50d4d5e63aedba21d/training/networks.py#L278) ``` self.affine = FullyConnectedLayer(w_dim, in_channels, bias_init=1) ```...