type
status
password
date
slug
summary
category
URL
tags
icon
函数 | 说明 |
evaluate.list_evaluation_modules(include_community=False, with_detai1s=True) | 查看可用评估函数 |
accuracy=evaluate.load("accuracy") | 加载评估函数 |
print(accuracy.description) | 查看评估指标说明 |
print(accuracy.inputs_description) | 查看评估指标的输入说明 |
accuracy.compute(references=[0, 1, 2, 0, 1, 2 ], predictions=[0, 1, 1, 2, 1, 0]) | 全局计算 |
accuracy = evaluate.load("accuracy")
for refs, pred in zip([[0,1],[0,1]],[[1,0],[0,1]]):
accuracy.add(references=refs predictions=preds)
accuracy.compute() | 迭代计算 |
clf_metrics=evaluate.combine(["accuracy","fl","recall ","precision"]) | 多种评估指标 |