Open Access

Fig. 12


Download original image

Schematics of the architecture of NN II: Converting displacement input tensor to vector via convolutional layers and merging with other inputs, obtaining latent vector through dense layer, and generating outputs via dense and convolutional layers.

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.