在 Keras 中向输出层添加新节点

Question

我想向输出层添加新节点以便稍后对其进行训练，我正在这样做：

def add_outputs(self, n_new_outputs):
    out = self.model.get_layer('fc8').output
    last_layer = self.model.get_layer('fc7').output
    out2 = Dense(n_new_outputs, activation='softmax', name='fc9')(last_layer)
    output = merge([out, out2], mode='concat')
    self.model = Model(input=self.model.input, output=output)

其中'fc7'是输出层之前的全连接层'fc8'。我希望只有最后一层，out = self.model.get_layer('fc8').output但输出是所有模型。有没有办法只从网络中获取一层？也许还有其他更简单的方法可以做到这一点......

谢谢！！！！

Answer 1

最后我找到了解决方案：

1）获取最后一层的权重

2）向权重添加零并随机初始化其连接

3）弹出输出层并创建一个新层

4）为新层设置新权重

这里是代码：

 def add_outputs(self, n_new_outputs):
        #Increment the number of outputs
        self.n_outputs += n_new_outputs
        weights = self.model.get_layer('fc8').get_weights()
        #Adding new weights, weights will be 0 and the connections random
        shape = weights[0].shape[0]
        weights[1] = np.concatenate((weights[1], np.zeros(n_new_outputs)), axis=0)
        weights[0] = np.concatenate((weights[0], -0.0001 * np.random.random_sample((shape, n_new_outputs)) + 0.0001), axis=1)
        #Deleting the old output layer
        self.model.layers.pop()
        last_layer = self.model.get_layer('batchnormalization_1').output
        #New output layer
        out = Dense(self.n_outputs, activation='softmax', name='fc8')(last_layer)
        self.model = Model(input=self.model.input, output=out)
        #set weights to the layer
        self.model.get_layer('fc8').set_weights(weights)
        print(weights[0])