The accuracy rate, recall rate, and F value are important evaluation indicators of the target in a mixed environment. In this paper, these three indicators are favored.
Let's take a look at the definition of these indicators first:
Accuracy Rate = Total number of correctly recognized individuals/total number of identified individuals
Recall rate = Total number of correctly recognized individuals/total number of individuals in the test set
F value = accuracy * recall rate * 2/(accuracy rate + recall rate)
For example, a pond contains 1400 carp, 300 shrimps, and 300 turtles. Now we aim to catch carp. Seaeagle sprinkled a large network, caught 700 carp, 200 shrimps, 100 turtles. These indicators are as follows:
Accuracy = 700/(700 + 200 + 100) = 70%
Recall rate = 700/1400 = 50%
F value = 70% * 50% * 2/(70% + 50%) = 58.3%
Let's take a look at the changes in these indicators if seaeagle does all the carp, prawns, and turtles in the pool:
Accuracy = 1400/(1400 + 300 + 300) = 70%
Recall rate = 1400/1400 = 100%
F value = 70% * 100% * 2/(70% + 100%) = 82.35%
It can be seen that the accuracy rate is the proportion of the target results in the captured results; the recall rate, as the name suggests, is the proportion of the target category in the field of interest; and the F value, this is an evaluation indicator that integrates the two indicators and is used to comprehensively reflect the overall indicators.
From: http://seaeagleforever.blog.163.com/blog/static/2111663020094222323671/