Fig. 4

Download original image
Representation of our convolutional neural network architecture. We show a 2D histogram of an E as an input example. Different layers of the network are displayed in various colors. The network is composed of 2 blocks of convolution layers, convolution layer, max pooling, and dropout. Then, we flatten the input and use two fully connected layers followed by the output layer. The output consists of a neuron with softmax activation. Table A.2 show the hyperparameters used in this architecture.
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.