Open Access

Fig. A.1.

image

Download original image

The encoder of VariLens. This module processes a batch of 5-band HSC images, each measuring 70 × 70 pixels, and compresses them into a latent representation of 64 dimensions. The batch size is flexible, with “None” meaning it can adapt based on user specifications. The leftmost column in the architecture diagram denotes the custom label and layer type, as defined by the TensorFlow deep learning framework.

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.