Striveworks/valor
Valor is a lightweight, numpy-based library designed for fast and seamless evaluation of machine learning models.
PythonNOASSERTION
Issues
- 0
BUG: Object Detection IOU Computation
#816 opened by czaloom - 0
- 0
ENH: Synthetic Benchmarking
#812 opened by czaloom - 0
- 0
ENH: Improve Object Detection PR Curve
#646 opened by czaloom - 0
- 0
ENH: Add progress reporting to evaluations.
#647 opened by czaloom - 0
ENH: Adjust `ConfusionMatrix` metric.
#807 opened by czaloom - 0
BUG: Incorrect F1 reported.
#808 opened by czaloom - 0
- 0
- 0
BUG: Obj Det confusion matrix OOM
#792 opened by czaloom - 0
- 0
ENH: Remove metrics_to_return.
#787 opened by czaloom - 0
ENH: Object Detection examples in dict format
#784 opened by czaloom - 0
BUG: ObjDet finalization slowdown
#782 opened by czaloom - 1
- 1
- 1
- 0
- 2
BUG: Valor Core Counting Datums with other label keys as true negative
#739 opened by jqu-striveworks - 2
BUG: Valor Core mAP is not calculated correctly when there are predictions for a class, but no ground truths
#736 opened by jqu-striveworks - 1
BUG: `lite` doesn't count true positives if there is a false positive with an equal score
#769 opened by ntlind - 0
ENH: Data filtering should affect returned metrics.
#766 opened by czaloom - 1
BUG: `lite` Counts are incorrect for a core test case
#757 opened by ntlind - 1
- 0
BUG: `lite` fails an AP test from `core`, likely due to an issue with selecting the "best pairs"
#754 opened by ntlind - 1
BUG: `valor_api.backend.core.label.validate_matching_label_keys` Fails unexpectedly
#640 opened by czaloom - 0
ENH: ability to search models and datasets
#750 opened by MattMcClainStrive - 2
- 0
BUG: Valor Core Classification Mislabels Prediction FP, FN, TN for examples.
#737 opened by jqu-striveworks - 1
Add smoothing function as a metric parameter for the BLEU text generation metric
#741 opened by bnativi - 0
adding support for NLP (?)
#665 opened by bnativi - 0
BUG: Filters Documentation not Rendering
#713 opened by czaloom - 1
BUG: Valor core classification PR curve computation uses lots of memory
#712 opened by rsbowman-striveworks - 0
- 0
- 0
BUG: `model.get_evaluations` returning empty list
#699 opened by ekorman - 0
ENH: Allow Precision and Recall MetricTypes for semantic segmentation
#683 opened by MattMcClainStrive - 0
ENH: Add client docs for MultiPolygon
#681 opened by czaloom - 0
- 0
Add 'memory used' to DatasetSummary
#669 opened by czaloom - 0
Optimize ROC AUC Computation
#666 opened by czaloom - 0
ENH: Allow Deletion Retry
#663 opened by czaloom - 0
BUG: Fix Benchmark Typo
#656 opened by czaloom - 0
- 0
BUG: Bulk `add_predictions` fails with `DatumAlreadyExistsError` or `AnnotationAlreadyExistsError`
#639 opened by czaloom - 0
BUG: Integration Test Fails Randomly
#653 opened by czaloom - 0
BUG: `validate_matching_label_keys` accessing data outside of user request scope.
#644 opened by czaloom - 0
BUG: Inconsistent evaluation times.
#641 opened by czaloom