Table 1

Hyperparameters.

Hyperparameters Value range
Learning rate 1e-3–1e-5
Batch size 16–128
Regularization term 0.01–0.1
Momentum 0.8–0.99
Noise dimension 32–128
Gradient penalty 10–50
Generator learning rate 1e-3–1e-5
Discriminator learning rate 1e-3–1e-5

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.