Table B.1.
Detailed single-channel architecture.
| # | Layer | Output Shape | Learnable Parameters |
|---|---|---|---|
| 1 | Input | [1, 256, 256] | 0 |
| 2 | Convolution | [64, 254, 254] | 640 |
| 3 | ReLU | [64, 254, 254] | 0 |
| 4 | MaxPooling | [64, 84, 84] | 0 |
| 5 | Convolution | [128, 82, 82] | 73 856 |
| 6 | ReLU | [128, 82, 82] | 0 |
| 7 | MaxPooling | [128, 27, 27] | 0 |
| 8 | Fully Connected | [1] | 93 313 |
| 9 | Sigmoid | [1] | 2 |
| Total Learnable Parameters | 167 809 | ||
Notes. From left to right columns, we list the layer number, layer type, output shape, and the total number of learnable parameters of the layer. The architecture is composed of two blocks of a convolutional layer, ReLU activation function, and max pooling layer, followed by an FC layer and a final sigmoid activation function.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.