Table 2 Output feature sizes for two quanvolutional layer.
From: Deep quanvolutional neural networks with enhanced trainability and gradient propagation
Input size | Residual configuration | Output feature size |
|---|---|---|
\(28\times 28\times 1\) | No residual | \(7\times 7\times 1\) |
\(28\times 28\times 1\) | \(X+O1\) | \(14\times 14\times 1\) |
\(28\times 28\times 1\) | \(O1+O2\) | \(14\times 14\times 1\) |
\(28\times 28\times 1\) | \(X+O2\) | \(28\times 28\times 1\) |
\(28\times 28\times 1\) | \((X+O1)+O2\) | \(28\times 28\times 1\) |
