Skip to main content

Table 2 Required times for training and test of deepGBLUP across marker densities and train sizes

From: deepGBLUP: joint deep learning networks and GBLUP framework for accurate genomic prediction of complex traits in Korean native cattle

Density

Train size

Training time (s)

Test time (s)

50K

9000

3.24

1.36

10K

9000

1.07

1.14

5K

9000

0.94

1.13

1K

9000

0.85

1.12

50K

5000

1.81

0.53

50K

2500

0.9

0.24

50K

1000

0.36

0.17

  1. We recorded the average time of four traits (CWT, BF, EMA, and MS). Training time means a processing time for 1 epoch