Open Access
Table A.2.
Architecture specifications for each layer of the 3D GAN generator network (G) and discriminator network (D) as well as the 3D AE’s encoder (E) and decoder(De).
| Filter sizes | {4, 4, 4, 4} |
|---|---|
| nfilter(G/De) | {128, 64, 32, 1} |
| nfilter(D/E) | {32, 64, 128, 256} |
| Strides: | {2, 2, 2, 2} |
| Layer Act. | ReLU (G/De), Leaky ReLU (D/E) |
| Final Act. | Tanh (G/De), Sigmoid (D), None(E) |
| Latent dimension | 200 |
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.