onemetric
Installation
-
Install onemetric from PyPI (recommended):
pip install onemetric -
Install onemetric from the GitHub source:
git clone https://github.com/SkalskiP/onemetric.git cd onemetric python setup.py install
Example
Figure 1. Dataset sample, blue - ground-truth and red - detection.
Calculate [email protected]
>>> from onemetric.cv.loaders import YOLOLoader
>>> from onemetric.cv.object_detection import MeanAveragePrecision
>>> model = load_model(...) # model-specific loading method
>>> data_set = YOLOLoader(
... images_dir_path=DATA_SET_IMAGES_PATH,
... annotations_dir_path=DATA_SET_ANNOTATIONS_PATH
... ).load()
>>> true_batches, detection_batches = [], []
>>> for entry in data_set:
>>> detections = model(entry.get_image()) # model-specific prediction method
>>> true_batches.append(entry.get_annotations())
>>> detection_batches.append(detections)
>>> mean_average_precision = MeanAveragePrecision.from_detections(
... true_batches=true_batches,
... detection_batches=detection_batches,
... num_classes=12,
... iou_threshold=0.5
... )
>>> mean_average_precision.value
0.61
Calculate Confusion Matrix
>>> confusion_matrix = ConfusionMatrix.from_detections(
... true_batches=true_batches,
... detection_batches=detection_batches,
... num_classes=12
... )
>>> confusion_matrix.plot(CONFUSION_MATRIX_TARGET_PATH, class_names=CLASS_NAMES)
Figure 2. Create confusion matrix chart
Documentation
The official documentation is hosted on Github Pages: https://skalskip.github.io/onemetric
Contribute
Feel free to file issues or pull requests. Let us know what metrics should be part of onemetric!
Citation
Please cite onemetric in your publications if this is useful for your research. Here is an example BibTeX entry:
@MISC{onemetric,
author = {Piotr Skalski},
title = {{onemetric}},
howpublished = "\url{https://github.com/SkalskiP/onemetric/}",
year = {2021},
}
License
This project is licensed under the BSD 3 - see the LICENSE file for details.
80 Dec 30, 2022
16.7k Jan 3, 2023
138 Dec 9, 2022
431 Jan 4, 2023
95 Nov 24, 2022
41 Dec 30, 2022
5.2k Jan 4, 2023
7.6k Jan 4, 2023
65.7k Jan 3, 2023
901 Dec 11, 2022
26 Dec 13, 2022
34 Nov 28, 2022
36 Dec 15, 2022
14 Aug 18, 2022
1 Jan 05, 2022
1 Oct 21, 2021
4 Nov 29, 2021
1.4k Dec 30, 2022
117 Nov 10, 2022
6 Dec 06, 2022
208 Nov 15, 2022
228 Dec 30, 2022
7 Aug 25, 2022
47k Jan 07, 2023
186 Dec 29, 2022
1.3k Jan 05, 2023
496 Jan 05, 2023
363 Dec 28, 2022