Skip to main content
. 2022 Apr 26;14:871706. doi: 10.3389/fnagi.2022.871706

Table 2.

Detailed parameters of our 2D-CNN slice sub-network.

Layer Kernel Stride Activation Output channels
Conv2D 3 × 3 2 BachNorm+Relu 8
MaxPooling2D 2 × 2 8
Conv2d 3 × 3 2 BachNorm+Relu 32
MaxPooling2D 2 × 2 32
Conv2D 3 × 3 2 BachNorm+Relu 64
MaxPooling2D 2 × 2 64
Global-Avg-Pooling2D 1 × 1 1 128
Full connected 128
Full connected 8