Search code examples
conv-neural-networkobject-detectionyolodarknet

What is the use of absolute, jitter, rescore and bias_match in YOLOv2 net in darknet?

Can someone explain me the following used in YOLOv2 net in darknet.

absolute=1
jitter=0.2
rescore=0
bias_match=1
Solution

  • jitter can be [0-1] and used to crop images during training for data augumentation. The larger the value of jitter, the more invariance would neural network to change of size and aspect ratio of the objects

    rescore determines what the loss (delta, cost, ...) function will be used

    bias_match used only for training, if bias_match=1 then detected object will have the same as in one of anchor, else if bias_match=0 then of anchor will be refined by a neural network.

    absolute is not used

    Look to great Alexey's answer for more explanation about cfg parameter : https://github.com/AlexeyAB/darknet/issues/279