Free Access

Table 1.

Architecture of the convolutional neural network.

No Layer Size output
1 Input 131 × 131 × 1
2 Conv2D 129 × 129 × n
3 MaxPooling2D 64 × 64 × n
4 Conv2D 62 × 62 × 2n
5 MaxPooling2D 31 × 31 × 2n
6 Conv2D 29 × 29 × 2n
7 MaxPooling2D 14 × 14 × 2n
8 Conv2D 12 × 12 × 2n
9 MaxPooling2D 6 × 6 × 2n
10 Conv2D 4 × 4 × 2n
11 MaxPooling2D 2 × 2 × 2n
12 Flatten 8n
13 Dropout 8n
14 Dense 8n
15 Dense 1

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.