Open Access
Table 1
Name of the model, size of the image patches (s), number of heads (h), number of transformer encoder layers (T), and the number of epochs taken to train the four vision models (e) in chronological order of creation.
| Model name | s | h | T | e |
|---|---|---|---|---|
| LSBG VISION 1 | 4 | 12 | 4 | 55 |
| LSBG VISION 2 | 4 | 12 | 8 | 55 |
| LSBG VISION 3 | 6 | 12 | 4 | 67 |
| LSBG VISION 4 | 6 | 16 | 8 | 67 |
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.