2martens
/
masterthesis
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Added missing functions to evaluate module doc 

Signed-off-by: Jim Martens <github@2martens.de>
This commit is contained in:
Jim Martens 2019-07-17 13:56:21 +02:00
parent b2e9a10bdf
commit f34eb93e71
1 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
src/twomartens/masterthesis/evaluate.py
View File

@ -20,8 +20,12 @@ Functionality to evaluate results of networks.
Functions:
get_number_gt_per_class(...): calculates the number of ground truth boxes per class
get_f1_score(...): computes the F1 score for every class
prepare-predictions(...): prepares the predictions for further processing
match_predictions(...): matches predictions to ground truth boxes
get_precision_recall(...): computes the precision and recall values and returns them
get_f1_score(...): computes the F1 score for every class
get_mean_average_precisions(...): computes the mean average precision for each class and returns them
get_mean_average_precision(...): computes the mean average precision over all classes and returns it
"""
from typing import Sequence, Union, Tuple, List