joaopauloschuler

@mikerabat , thank you for sharing it! I'm certain that there are other users that will benefit from your branch. I'll eventually look at it with care. One thing I'm...

This is an excellent question that opens up plenty of passionate debate. When I am renting hardware to run my own models, I prefer renting CPU only hardware without GPU....

Hello @mikerabat , There is a curse in computer science: **algorithms can always be improved making the job never ending**. Regarding "_A colleague of mine made the comment I should...

Dear @mikerabat ! Feel free to use 512 input channels (instead of 3 for RGB) and beyond if you need. I have already used more than 512 channels with hyperspectral...

Doubling the filter size at each maxpool or stride is a good idea.

I would use fully connected layers with maxpool only for the actual image classification (not for the autoencoder).

Dear @mikerabat , have a look at this link please: https://poe.com/s/zm7ERt1OgV8SsRw4WWX8 . The reply was given by Claude (not me - although Claude signed as me). In my opinion, my...

I would change this: ``` NN.AddLayer( TNNetConvolutionReLU.Create( 8, 3, 1, 1, 1 ) ); NN.AddLayer( TNNetUpsample.Create() ); NN.AddLayer( TNNetConvolutionReLU.Create( 8, 3, 1, 1, 1 ) ); ``` to this: ```...

AH! I now understand what you say. I see: the padding is making the second dimension to grow. In the encoder side, what you can do is: * In the...

In this message, I'm not suggesting anything. I'm just bringing to attention existing layers. Via transposing outputs and running pointwise convolutions, you can transform a 2D output into a cube....