Finger Vein Verification on Different Datasets Based on Deep Learning with Triplet Loss

Table 2

Number of valid training triplets as the training epoch increases (an example from this experiment).

Epoch	1	2	3	4	5	6	7	8	9	10
No. of valid training triplets	9943	1338	725	502	344	273	256	178	155	151
Epoch	11	12	13	14	15	16	17	18	19	20
No. of valid training triplets	124	122	95	88	76	72	71	70	57	42