AutoML Video Inteligence with custom labels - true negatives in training data

Question

This question pertains to AutoML for Video Intelligence (custom labels).

When setting up training data, you are instructed to only label videos with your custom labels in them (and not videos that don’t have that label). How does the model train to identify true negatives for custom labels?

score 0 · Answer 1 · answered May 07 '19 at 02:05

0

After applying the score threshold, the predictions made by your model will fall in one of the following four categories.

We can use these categories to calculate precision and recall — metrics that help us gauge the effectiveness of our model.

answered May 07 '19 at 02:05

Bira

4,531
2
27
42

Thanks - does this mean that for each custom label, it determines the subset of your videos that do not have that label, and trains on that info? – CCC May 08 '19 at 14:38

AutoML Video Inteligence with custom labels - true negatives in training data

1 Answers1