How to understand YOLO_LABELS in noscope_motherdog.py about noscope HOT 2 CLOSED

I found the answer. The meanings are:
0 means “yolo_label_num”
[("coral-reef-long_convnet_32_32_1.pb", None),
("coral-reef-long_convnet_32_32_2.pb", None),] is the pipelines
648000 + 1188000 is the TRAIN_START_IDX
1188000 is the TRAIN_LEN,
648000 + 1188000 * 2 is the TEST_START_IDX,
1188000 is the TEST_LEN

from noscope.

@janhuang6 Is pipeline just the cnn model? Why is there only two instead of all the 12 CNN's they've trained?
Also, do you know how they index the videos? I thought there were only 1188000 frames, and 648000 + 1188000 would be out of range.

from noscope.