重塑层，但不会重塑

Question

大家好，同时添加一个简单而琐碎的 Keras Reshape图层来重塑我的卷积中的图像

    decoder = BatchNormalization()(decoder)
    decoder = Reshape((224 * 512, n_classes), input_shape=(224, 512, 3))(decoder)

    predictions = Activation('softmax')(decoder)

运行时出现此错误

ValueError: Error when checking target: expected activation_13 to have 3 dimensions, but got array with shape (8, 224, 512, 3)

奇怪的是，它出现在图表中：

batch_normalization_13 (Batc (None, 224, 512, 3)       12
_________________________________________________________________
reshape_1 (Reshape)          (None, 114688, 3)         0
_________________________________________________________________
activation_13 (Activation)   (None, 114688, 3)         0
______________________________________________________________

Answer 1

这是预期的行为，错误是抱怨批量大小，因此您的最终输出是3维，如摘要中所示。问题是你的目标，火车没有重新塑造。您需要重塑目标数组，传递的数组适合形状(samples, 114688, 3)的3D张量。