keras：model.predict和model.predict_proba有什么区别 [英] keras: what is the difference between model.predict and model.predict_proba

问题描述

我发现 model.predict 和 model.predict_proba 都给出了相同的2D矩阵，表示每个类别的概率每一行。

I found model.predict and model.predict_proba both give an identical 2D matrix representing probabilities at each categories for each row.

这两个函数有什么区别？

What is the difference of the two functions?

推荐答案

预测

predict(self, x, batch_size=32, verbose=0)

生成输入样本的输出预测，以批处理方式处理样本。

Generates output predictions for the input samples, processing the samples in a batched way.

参数

x: the input data, as a Numpy array.
batch_size: integer.
verbose: verbosity mode, 0 or 1.

返回

A Numpy array of predictions.

predict_proba

predict_proba(self, x, batch_size=32, verbose=1)

逐批生成输入样本的类别概率预测。

Generates class probability predictions for the input samples batch by batch.

参数

x: input data, as a Numpy array or list of Numpy arrays (if the model has multiple inputs).
batch_size: integer.
verbose: verbosity mode, 0 or 1.

返回

A Numpy array of probability predictions.

编辑：在最新版本的keras中，predict和predict_proba相同即都给出概率。要获取类标签，请使用predict_classes。该文档未更新。 （根据Avijit Dasgupta的评论改编）

Edit: In the recent version of keras, predict and predict_proba is same i.e. both give probabilities. To get the class labels use predict_classes. The documentation is not updated. (adapted from Avijit Dasgupta's comment)

这篇关于keras：model.predict和model.predict_proba有什么区别的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！