joaopauloschuler

The request is valid and I'm still considering it.

Good question. This building block is described in these 2 papers: - [Grouped Pointwise Convolutions Significantly Reduces Parameters in EfficientNet.](https://www.researchgate.net/publication/355214501_Grouped_Pointwise_Convolutions_Significantly_Reduces_Parameters_in_EfficientNet) - [Grouped Pointwise Convolutions Reduce Parameters in Convolutional Neural Networks.](https://www.researchgate.net/publication/360226228_Grouped_Pointwise_Convolutions_Reduce_Parameters_in_Convolutional_Neural_Networks)...

I like having IFDEFS... I'll probably be too busy to code AVX support on Delphi for the next 7 months. Open source code can always be forked... With the proper...

@mikerabat , I'm certainly interested. I'll try to figure why the pull request didn't work.

@mikerabat , I can see plenty of coding. It will take me some time to test it in all supported environments. Most likely, I'll ask you to create a new...

Hi, In the case that you could have your input as SizeX=10, SizeY=1 and Depth=4, I could see 2 steps: 1. Separate the input according to the channel (or depth)....

Hi, I probably miss understood you. I thought that you had 4 portions of 10 values each. In this understanding, you could create 4 channels (depth = 4). If this...

Hi, I'm wondering if you could shape your input to something like this: SizeX=1, SizeY=1, Depth=40 (or any number). Then, you could copy portions of the input with `TNNetSplitChannels.Create(ChannelStart, ChannelLen:...

New compute methods have been added allowing multiple inputs: ``` procedure Compute(pInput: array of TNeuralFloatDynArr); overload; procedure Compute(pInput: array of TNeuralFloat; FromLayerIdx:integer = 0); overload; ``` It's assumed that first...

I updated the example. Have a look please if it makes more sense. I'm submitting both inputs with the same data just to show the syntax (it doesn't make sense...