Changelog¶
All notable changes to this project will be documented in this file.
The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.
[0.3.1] - 2021-04-21¶
[0.3.0] - 2021-04-20¶
[0.3.0] - Added¶
Added
BootStrapper
to easily calculate confidence intervals for metrics (#101)Added Binned metrics (#128)
Added metrics for Information Retrieval ((PL^5032)):
Added other metrics:
Added
average='micro'
as an option in AUROC for multilabel problems (#110)Added multilabel support to
ROC
metric (#114)Added
AverageMeter
for ad-hoc averages of values (#138)Added
prefix
argument toMetricCollection
(#70)Added
__getitem__
as metric arithmetic operation (#142)Added property
is_differentiable
to metrics and test for differentiability (#154)Added support for
average
,ignore_index
andmdmc_average
inAccuracy
metric (#166)Added
postfix
arg toMetricCollection
(#188)
[0.3.0] - Changed¶
Changed
ExplainedVariance
from storing all preds/targets to tracking 5 statistics (#68)Changed behaviour of
confusionmatrix
for multilabel data to better matchmultilabel_confusion_matrix
from sklearn (#134)Updated FBeta arguments (#111)
Changed
reset
method to usedetach.clone()
instead ofdeepcopy
when resetting to default (#163)Metrics passed as dict to
MetricCollection
will now always be in deterministic order (#173)Allowed
MetricCollection
pass metrics as arguments (#176)
[0.1.0] - 2021-02-22¶
Added
Accuracy
metric now generalizes to Top-k accuracy for (multi-dimensional) multi-class inputs using thetop_k
parameter (PL^4838)Added
Accuracy
metric now enables the computation of subset accuracy for multi-label or multi-dimensional multi-class inputs with thesubset_accuracy
parameter (PL^4838)Added
HammingDistance
metric to compute the hamming distance (loss) (PL^4838)Added
StatScores
metric to compute the number of true positives, false positives, true negatives and false negatives (PL^4839)Added
R2Score
metric (PL^5241)Added
MetricCollection
(PL^4318)Added
.clone()
method to metrics (PL^4318)Added
IoU
class interface (PL^4704)The
Recall
andPrecision
metrics (and their functional counterpartsrecall
andprecision
) can now be generalized to Recall@K and Precision@K with the use oftop_k
parameter (PL^4842)Added compositional metrics (PL^5464)
Added AUC/AUROC class interface (PL^5479)
Added
QuantizationAwareTraining
callback (PL^5706)Added
ConfusionMatrix
class interface (PL^4348)Added multiclass AUROC metric (PL^4236)
Added
PrecisionRecallCurve, ROC, AveragePrecision
class metric (PL^4549)Classification metrics overhaul (PL^4837)
Added
F1
class metric (PL^4656)Added metrics aggregation in Horovod and fixed early stopping (PL^3775)
Added
persistent(mode)
method to metrics, to enable and disable metric states being added tostate_dict
(PL^4482)Added unification of regression metrics (PL^4166)
Added persistent flag to
Metric.add_state
(PL^4195)Added classification metrics (PL^4043)
Added EMB similarity (PL^3349)
Added SSIM metrics (PL^2671)
Added BLEU metrics (PL^2535)