Python 3.x 向Keras中的输出层添加新节点
我想向输出层添加新节点,以便稍后对其进行训练,我正在执行以下操作:Python 3.x 向Keras中的输出层添加新节点,python-3.x,neural-network,deep-learning,keras,keras-layer,Python 3.x,Neural Network,Deep Learning,Keras,Keras Layer,我想向输出层添加新节点,以便稍后对其进行训练,我正在执行以下操作: 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)
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'fc8'
之前的完全连接层。我只希望有最后一层out=self.model.get_layer('fc8')。output
,但输出都是模型。
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
谢谢 最后我找到了一个解决方案: 1) 从最后一层获取权重 2) 将零添加到权重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 代码如下:
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])