Question

我正在使用具有张量流后端的Keras 2.04。我想在MNIST图像上用ImageDataGenerator训练一个简单的模型。但是，我一直从fit_generator收到以下错误：

ValueError：检查输入时出错：期望input_1有2 尺寸，但有阵列形状（8,28,28,1）。

这是代码：

#loading data & reshaping
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = x_train.reshape(x_train.shape[0], 28, 28,1)

#building the model
input_img = Input(shape=(784,))
encoded = Dense(30, activation='relu')(input_img)
decoded = Dense(784, activation='sigmoid')(encoded)
autoencoder = Model(input_img, decoded)
autoencoder.compile(optimizer='adam', loss='mse')

#creating ImageDataGenerator
datagen = ImageDataGenerator(featurewise_center=True, featurewise_std_normalization=True)
datagen.fit(x_train)

autoencoder.fit_generator(
        #x_train, x_train because the target is to reconstruct the input
        datagen.flow(x_train, x_train, batch_size=8),
        steps_per_epoch=int(len(x_train)/8),
        epochs=64,
       )

据我所知，ImageDataGenerator应该每次迭代生成一批训练样例，就像它实际上一样（在这种情况下，batch_size = 8）但是从错误中看起来好像它需要一个训练样例。

谢谢！

Answer 1

解决了 - 应该是：

autoencoder = Sequential()
autoencoder.add(Reshape((784,), input_shape=(28,28,1)))
autoencoder.add(Dense(30, activation='relu'))
autoencoder.add(Dense(784, activation='relu'))
.
.
.

autoencoder.fit_generator(
        datagen.flow(x_train, x_train.reshape(len(x_train),784,), batch_size=8),
        steps_per_epoch=int(len(x_train)/8),
        epochs=64,
       )

使用ImageDataGenerator（Keras）时fit_generator输入尺寸错误

1 个答案: