A collection of diverse metrics to analyse performance of Machine Learning and Deep Learning Models. This includes a variety of functions for Classification, Regression, Natural Language Processing, Computer Vision and Ranking Models and also utilities for better user support.
To install Metrics.jl, you need to fill in the following code into the Julia Prompt
] add Metricsor
using Pkg
Pkg.add("Metrics")using Metrics
# get accuracy with default threshold = 0.5
acc = Metrics.binary_accuracy(y_pred, y_true)
# get complete stats including Confusion Matrix, Accuracy, Precision, Recall, F1 Score, etc.
Metrics.report_stats(y_pred, y_true) # where y_pred are the predicted values and y_true are onehot_encoded ground truth valuesFor more details about the package and the functions, check out the documentation. In case you have any questions, you can tag me (@Adarsh Kumar) in Julia's slack, or you can just create an issue on Github.