keras多输出softmax模型输入形状

Question

我有以下型号：

from keras.layers import Activation, Input, Dense
from keras.models import Model
from keras.layers.merge import Concatenate, concatenate

input_ = Input(batch_shape=(512, 36))

x = input_
x1 = Dense(4)(x)
x2 = Dense(4)(x)
x3 = Dense(4)(x)
x4 = Dense(4)(x)

model = Model(inputs=input_, outputs=[x1, x2, x3, x4])
model.compile(loss='categorical_crossentropy', optimizer='adam',  metrics=['accuracy'])
history = model.fit(X, test, epochs=20, batch_size=512, verbose=2, shuffle=False, validation_data=[X, test])

我的Y具有以下格式：

 col1 col2 ... col 4
  1    0         2
  0    0         2
  2    1         1

并通过以下方式重新塑造：

y = to_categorical(Y).reshape(4, -1, 3)

但是，运行fit命令时，我收到以下错误：

ValueError: Error when checking model target: the list of Numpy arrays that 
you are passing to your model is not the size the model expected. Expected 
to see 4 array(s), but instead got the following list of 1 arrays: 
[array([[[1., 0., 0.],
    [1., 0., 0.],
    [1., 0., 0.],

Answer 1

假设Y是一个numpy矩阵？试试这个：

y = [to_categorical(Y[:, col_numb]).reshape(-1, 3) for col_numb in range(Y.shape[1])]