org.apache.clojure-mxnet.eval-metric — org.apache.clojure-mxnet/clojure-mxnet 0.1.0-SNAPSHOT

accuracy clj

(accuracy)

Basic Accuracy Metric

custom-metric clj/s macro

(custom-metric f-eval mname)

Custom evaluation metric that takes a NDArray function.

• f-eval Customized evaluation function that takes two ndarrays and returns a number function must be in the form of (fn [] ) clojure style
• mname The name of the metric

f1 clj

(f1)

Calculate the F1 score of a binary classification problem.

get clj

(get metric)

Get the values of the metric in a vector form (name and value)

get-and-reset clj

(get-and-reset metric)

Get the values and then reset the metric

mae clj

(mae)

Calculate Mean Absolute Error loss

mse clj

(mse)

Calculate Mean Squared Error loss

perplexity clj

(perplexity)

(perplexity {:keys [ignore-label axis] :as opts :or {axis -1}})

Calculate perplexity

• opts :ignore-label Index of invalid label to ignore when counting. Usually should be -1. Include all entries if None. :axis The axis from prediction that was used to compute softmax. Default is -1 which means use the last axis.

reset clj

(reset metric)

clear the internal statistics to an initial state

rmse clj

(rmse)

Calculate Root Mean Squred Error loss

top-k-accuracy clj

(top-k-accuracy top-k)

Calculate to k predications accuracy

• top-k number of predicts (int)

update clj

(update metric labels preds)

Update the internal evaluation