Difference between model.evaluate vs model.predict in Keras

The model.evaluate function predicts the output for the given input and then computes the metrics function specified in the model.compile and based on y_true and y_pred and returns the computed metric value as the output.

The model.predict just returns back the y_pred .

model.evaluate函数预测给定输入的输出,然后计算model.compile中指定的metrics函数,并基于y_true和y_pred,并返回计算的度量值作为输出。

model.predict只返回y_pred。

model.evaluate 用于评估您训练的模型。它的输出是准确度或损失,而不是对输入数据的预测。

model.predict 实际预测,其输出是目标值,根据输入数据预测。

来源: https://www.quora.com/What-is-the-difference-between-keras-evaluate-and-keras-predict