Keras TypeError:fit()缺少1个必需的位置参数:"y" [英] Keras TypeError: fit() missing 1 required positional argument: 'y'

问题描述

我的模型格式正确:

model = Sequential()
model.add(Lambda(lambda x:x/255.0 - 0.5, input_shape=(160,320,3)))
model.compile(loss='mse', optimizer='adam')
model.fit(train_generator, samples_per_epoch= len(train_samples), validation_data=validation_generator, nb_val_samples=len(validation_samples), nb_epoch=3)

请注意，括号已到位.但是，当我适合时，会出现以下错误:

Note, parenthesis are in place. However when I fit I get the following error:

Traceback (most recent call last):   File "modell.py", line 70, in <module>
    model.fit(train_generator, samples_per_epoch= len(train_samples), validation_data=validation_generator, nb_val_samples=len(validation_samples), nb_epoch=3) 
TypeError: fit() missing 1 required positional argument: 'y'

train_generator是2D数组

train_generator = generator(train_samples, batch_size=32)

我必须是盲人，因为我无法发现问题.有谁知道为什么fit在寻找额外的论点?

I must be blind because I can't spot the problem. Does anyone know why fit is looking for an extra argument?

推荐答案

在使用生成器进行训练时，必须使用方法model.fit_generator.

When using a generator to train, you must use the method model.fit_generator.

方法fit将始终要求输入(X)和输出/目标(Y)

The method fit will always demand for inputs (X) and outputs/targets (Y)

这篇关于Keras TypeError:fit()缺少1个必需的位置参数:"y"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！