Toluwani Aremu

## Question **conv2d_im2col wrapper file** ## Further Information I'm trying to understand the image to vector encoding for the ckks encryption., however I can only find the class definition within...

support for maxpool, avgpool layers

4

## Question self.conv1_weight = torch_nn.conv1.weight.data.view( torch_nn.conv1.out_channels, torch_nn.conv1.kernel_size[0], torch_nn.conv1.kernel_size[1] ).tolist() self.conv1_bias = torch_nn.conv1.bias.data.tolist() Can we also use this idea for maxpool and avgpool layers i.e. self.maxpool_weight = torch_nn.maxpool.weight.data.view( torch_nn.maxpool.kernel_size[0], torch_nn.maxpool.kernel_size[1] ).tolist()...

Dataset encryption before model learning

2

Hello! How do I encrypt a dataset before passing it into a dataloader and then sending it into an architecture for training?

1. Is it possible to perform a transpose in the spectral domain? 2. FFTConv2d(in,out,.......) initializes weights just like conv?

This is an issue concerning the architectural arrangement. In deeper layers, for example, in Resnet18, changing all convolutional layers to kervolutional layers (with degree 3), the network gives a NaN...