Table 2 Architectures of basic CNN
From: Microaneurysm detection in fundus images using a two-step convolutional neural network
Layer | Operation | Input size | Detail | Berr, (p) |
|---|---|---|---|---|
Layer 1 | Input | \(3\times 101\times 101\) | – | – |
Layer 2 | Convolutional | \(16\times 96\times 96\) | \(7\times 7\) | – |
Layer 3 | Max pooling | \(16\times 48\times 48\) | \(2\times 2\) | 0.25 |
Layer 4 | Convolutional | \(16\times 44\times 44\) | \(5\times 5\) | – |
Layer 5 | Max pooling | \(16\times 22\times 22\) | \(2\times 2\) | 0.25 |
Layer 6 | Convolutional | \(16\times 20\times 20\) | \(3\times 3\) | – |
Layer 7 | Max pooling | \(16\times 10\times 10\) | \(2\times 2\) | 0.25 |
Layer 8 | Fully connected | 200 | \(1\times 1\) | – |
Layer 9 | Fully connected | 100 | \(1\times 1\) | – |
Layer 10 | Fully connected | 2 | \(1\times 1\) | – |