How to understand YOLO_LABELS in noscope_motherdog.py

[janhuang6]

I see this in noscope_motherdog.py:

YOLO_LABELS["coral-reef-long"] = ( 0, [("coral-reef-long_convnet_32_32_1.pb", None), ("coral-reef-long_convnet_32_32_2.pb", None),], 648000 + 1188000, 1188000, 648000 + 1188000 * 2, 1188000 )

So what do those numbers mean? Is there a document explaining those? I really need to understand those so I can add my own YOLO_LABELS["my-video"] session with the correct numbers to have Yolo process my video.

Right now, Yolo is not processing my video correctly because those numbers are not setup right.

[janhuang6]

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

[sxhexe]

@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.