O’TRAIN: A robust and flexible ‘real or bogus’ classifier for the study of the optical transient sky

Open Access

Table 3

Summary of the different data cube configurations used to train our O’TRAIN CNN.

Tel. name	Detection pipeline	Number of candidates	True/False %	Cutouts size (pixels)
JAST	gmadet	13 558	50/50	32 × 32
JAST	STDPipe	18 328	50/50	32 × 32
FRAM	gmadet	8906	50/50	32 × 32
TACA	gmadet	18450	50/50	32 × 32
TCA	gmadet	11414	50/50	32 × 32

Notes. The number of candidates reported is the sum of the labelled ‘True’ and ‘False’ candidates stored in the respective data cubes.

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.