Akanimax
Akanimax
@ibmua , do you have your paper somewhere?
I am facing some issues in understanding the api usage since I couldn't find enough examples. Besides the existing examples are unfortunately not very clear. It would be a great...
I looked everywhere but, couldn't find proper resources for this library. Finally, I am writing this as an issue. I am using this library with your quepy library for converting...
In your code here: [`x = self.conv(x.mul(self.scale))`](https://github.com/nashory/pggan-pytorch/blob/master/custom_layers.py#L113), the input `x` is multiplied by the `scale` which is equal to `scale = sqrt(2 / fan_in)` from HE initializer. I am a...
The flow of tensors is not visible in the graph. The name and variable scoping is not done properly due to which, the tensorboard graph visualizer ends up creating a...
Hello, @huangzh13, Firstly, great job on the code. It's quite good. I just wanted to point out that there could be a possible mistake in porting the official tensorflow pretrained...
@huangzh13, At the outset, this is a great implementation of StyleGAN in PyTorch. I really like the way the modules are structured. This is more of a suggestion from my...
Doing an informal test the other day, it seems like some operations have slowed down quite a bit since the new changes. Need to add profiling options to the code...
Hi @mkocabas, There is a slight mismatch in the notation used to denote the extracted dimensions from the shape of the input tensor. [here](https://github.com/mkocabas/CoordConv-pytorch/blob/master/CoordConv.py#L84) batch_size, _, x_dim, y_dim = input_tensor.size()...
The code organization is very good resulting in a clean and readable implementation of the SEGNET architecture. Good Job :+1:. However, the training loop is implemented by using the lower...