Keras 拟合模型：类型错误：不可散列类型："numpy.ndarray"

Question

我实现以下代码。它在以前版本的 Keras 中成功运行：

max_sequence = 56
input_dim = 26    
print("Build model..1")
first_input = Input(shape=(max_sequence,input_dim))
first_lstm = LSTM(5, return_sequences=True)(first_input)
first_bn = BatchNormalization()(first_lstm)
first_activation = Activation('tanh')(first_bn)
first_flat = Flatten()(first_activation)
print("Build model..2")
second_input = Input(shape=(max_sequence,input_dim))
second_lstm = LSTM(5, return_sequences=True)(second_input)
second_bn = BatchNormalization()(second_lstm)
second_activation = Activation('tanh')(second_bn)
second_flat = Flatten()(second_activation)
merge=concatenate([first_flat, second_flat])
merge_dense=Dense(3)(merge)
merge_bn = BatchNormalization()(merge_dense)
merge_activation = Activation('tanh')(merge_bn)
merge_dense2=Dense(1)(merge_activation)
merge_activation2 = Activation('tanh')(merge_dense2)
train_x_1 = np.reshape(np.array(train_x_1), [2999, 56, 26])
train_x_2 = np.reshape(np.array(train_x_2), [2999, 56, 26])

model=Model(inputs=[train_x_1,train_x_2], outputs=train_y_class)
optimizer = RMSprop(lr=0.5)
model.compile(optimizer=optimizer, loss='binary_crossentropy', metrics=['accuracy'])

history = model.fit([train_x_1, train_x_2], train_y_class, nb_epoch=300, batch_size=128,
validation_data=([val_x_1, val_x_2], val_y_class))

运行时：

history = model.fit([train_x_1, train_x_2], train_y_class, nb_epoch=300, batch_size=128,
validation_data=([val_x_1, val_x_2], val_y_class))

发生以下错误：

TypeError: unhashable type: 'numpy.ndarray' accours.

所以我检查了train_x_1、train_x_2、train_y_class。他们的类型是<class 'numpy.ndarray'>.我已经寻找了一个解决方案，所以我试图将类型更改为元组，但它不起作用。

如果numpy.ndarray不可散列，model.fit接收什么类型的输入？

训练数据的形状如下：

train_x_1.shape
(2999, 56, 26)
train_x_2.shape
(2999, 56, 26)
train_y_class.shape
(2999, 1)

train_x_1示例如下所示：

array([[[ 1.62601626e-02,  2.26890756e-01,  1.17764920e-02, ...,
0.00000000e+00,  0.00000000e+00,  0.00000000e+00],
[ 1.62601626e-02,  2.26890756e-01,  1.17764920e-02, ...,
0.00000000e+00,  0.00000000e+00,  0.00000000e+00],
[ 1.62601626e-02,  2.26890756e-01,  1.17764920e-02, ...,
0.00000000e+00,  0.00000000e+00,  0.00000000e+00],
...,
[ 1.62601626e-02,  2.26890756e-01,  1.17764920e-02, ...,
0.00000000e+00,  0.00000000e+00,  0.00000000e+00],
[ 1.62601626e-02,  2.26890756e-01,  1.17764920e-02, ...,
0.00000000e+00,  0.00000000e+00,  0.00000000e+00],
[ 1.62601626e-02,  2.26890756e-01,  1.17764920e-02, ...,
0.00000000e+00,  0.00000000e+00,  0.00000000e+00]],

Answer 1

问题是在构造模型时，您将输入和输出数组(而不是输入和输出张量(直接传递给Model类：

model = Model(inputs=[train_x_1,train_x_2], outputs=train_y_class)

相反，您需要像这样传递相应的输入和输出张量：

model = Model(inputs=[first_input,second_input], outputs=merge_activation2)