Free Access

Fig. 3.

image

Download original image

Results when the network is applied outside of the domain of the training data. Left column: strongly lensed images used as input to the neural network. Middle column: pixel-by-pixel labels we want the network to reproduce. Right column: network predictions. The input images assume one full orbit of exposure for an apparent magnitude-19 source. Animations are available online.

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.