4

What does means in YOLOv5 the metric "mAP_0.5"?

If we arrive at N iterations and its value is constant, what does it mean?

Lastly, what the training loss metrics, "box loss" and "obj loss", mean ?

Is it normal that by increasing the number of iterations the graphs of these two metrics have a decreasing trend? What is the significance of this behavior?

Thanks!

compup
  • 77
  • 1
  • 8
  • `mAP` is mean average precision with `IOU`(Intersection Over Union) of `0.5`. Follow the `metrics` section for more details, https://cocodataset.org/#detection-eval. – B200011011 Mar 04 '21 at 23:18

2 Answers2

4

For mAP_0.5 I refer you to this blog post: https://jonathan-hui.medium.com/map-mean-average-precision-for-object-detection-45c121a31173

The "box loss" represents how well the algorithm can locate the centre of an object and how well the predicted bounding box covers an object. Objectness is essentially a measure of the probability that an object exists in a proposed region of interest. If the objectivity is high, this means that the image window is likely to contain an object. Classification loss gives an idea of how well the algorithm can predict the correct class of a given object. [1]

The losses should be decreasing up to a saturating point and this behavior is normal.

[1] https://www.mdpi.com/1999-4893/14/4/114

Erfan
  • 352
  • 3
  • 8
0

The train box loss metric measures the difference between the predicted bounding boxes and the actual bounding boxes of the objects in the training data. A lower box loss means that the model's predicted bounding boxes more closely align with the actual bounding boxes.

Hasibullah Aman
  • 1
  • 2