Question

我正在使用Keras和Theano训练神经网络，其中输入的格式如下：

[
   [Situation features],
   [Option 1 features],
   [Option 2 features],
]

我想训练一个模型来预测每个选项的选择频率，让模型学会如何评分每个选项，以及情况如何使分数差异更重要或更不重要。

我的模型看起来像：

option_inputs = [Input(shape=(NUM_FEATURES,), name='situation_input'),
                  Input(shape=(NUM_FEATURES,), name='option_input_0'),
                  Input(shape=(NUM_FEATURES,), name='option_input_1')]
situation_input_processing = Dense(5, activation='relu', name='situation_input_processing')
option_input_processing = Dense(20, activation='relu', name='option_input_processing')
diversity_neuron = Dense(1, activation='softplus', name='diversity_neuron')
scoring_neuron = Dense(1, activation='linear', name='scoring_neuron')

diversity_output = diversity_neuron(situation_input_processing(journey_inputs[0]))
scoring_outputs = [scoring_neuron(option_input_processing(option_input)) for option_input in option_inputs[1:2]]

logit_outputs = [Multiply()([diversity_output, scoring_output]) for scoring_output in scoring_outputs]
probability_outputs = Activation('softmax')(keras.layers.concatenate(logit_outputs, axis=-1))

model = Model(inputs=option_inputs, outputs=probability_outputs)

尝试获取probability_outputs时，出现错误：

ValueError：Concatenate图层应在输入列表
上调用

似乎触发了错误，因为logit_outputs没有在所有3个输入要素集合中迭代构建，只有2个输入。

知道如何解决这个问题吗？

对模型进行训练后，我想观察diversity_neuron和scoring_neuron的输出，以了解如何推断任意数量选项的得分，并了解驱动多样性的因素。

Answer 1

我已经做了这些更改来解决问题：

我在每个选项的开头都包含了情境特征功能列表
我添加了一个可以过滤情况的图层选项输入的功能。这是通过手动设置完成的不可训练层的重量。
然后我可以遍历所有在网络的任何路径中输入

最终代码如下：

option_inputs = [Input(shape=(NUM_FEATURES,), name='option_input_0'),
                  Input(shape=(NUM_FEATURES,), name='option_input_1')]
situation_input_filtering = Dense(NUM_SITUATION_FEATURES, activation='linear', name='situation_input_filtering')
situation_input_filtering.trainable = False
situation_input_processing = Dense(5, activation='relu', name='situation_input_processing')
option_input_processing = Dense(20, activation='relu', name='option_input_processing')
diversity_neuron = Dense(1, activation='sigmoid', name='diversity_neuron')
scoring_neuron = Dense(1, activation='linear', name='scoring_neuron')

diversity_outputs = [diversity_neuron(situation_input_processing(situation_input_filtering(option_input))) for
                     option_input in option_inputs]
scoring_outputs = [scoring_neuron(option_input_processing(option_input)) for option_input in option_inputs]

logit_outputs = [Multiply()([diversity_output, scoring_output]) for diversity_output, scoring_output in
                 zip(diversity_outputs, scoring_outputs)]
combined = keras.layers.concatenate(logit_outputs, axis=-1)
probability_outputs = Activation('softmax')(combined)

model = Model(inputs=option_inputs, outputs=probability_outputs)
model.compile(optimizer='adadelta', loss='categorical_crossentropy', metrics=['accuracy'])

mask_weights = np.zeros([NUM_FEATURES, NUM_SITUATION_FEATURES])
for i in xrange(NUM_situation_FEATURES):
    mask_weights[i, i] = 1.0

for layer in model.layers:
    if layer.name == 'situation_input_filtering':
        layer.set_weights([mask_weights, np.zeros(NUM_SITUATION_FEATURES)])

Keras：如何连接输入子集

1 个答案: