我有一個通過 Keras 功能 API 定義的自定義 ResNet 模型。我的模型也有多個輸出。輸出陣列的最后一個元素是具有num_class節點的全連接密集層。我希望能夠增加這一層的節點數。這是創建我的網路的相關代碼：
from tensorflow.keras import layers, models, Input, regularizers
res = []
inputs = Input(shape=(height, width, channels), name='data')
x = MyLayer()(inputs)
# ... other layers
x = MyLayer()(x)
res.append(x)
# ... other layers
x = layers.Dense(num_class, name='fc1', use_bias=True)(x)
res.append(x)
model = models.Model(inputs=inputs, outputs=[res[-2], res[-3], res[-4], res[-1]])
在向 Keras 中的輸出層添加新節點的問題中，我找到了一個類似于我正在搜索的答案，我在下面添加：
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])
然而，在這個問題中，只有一層作為輸出，我不確定如何在我的架構中復制它。
uj5u.com熱心網友回復：
這是我想出的解決方案。我將想要保留作為輸出的層分配給變數：
from tensorflow.keras import layers, models, Input, regularizers
inputs = Input(shape=(height, width, channels), name='data')
x = MyLayer()(inputs)
# ... other layers
a = MyLayer(name="a")(x)
b = MyLayer(name="b")(a)
c = MyLayer(name="c")(b)
x = layers.Dense(num_class, name='fc1', use_bias=True)(c)
model = models.Model(inputs=inputs, outputs=[c, b, a, x])
然后為了增加最后一層的節點數，只需呼叫該函式即可increment_classes。節點總數將是 和 的old_num_class總和num_class。
def increment_classes(model, old_num_class, num_class):
weights = model.get_layer("fc1").get_weights()
new_num_class = old_num_class num_class
# Adding new weights, weights will be 0 and the connections random
shape = weights[0].shape[0]
weights[1] = np.concatenate((weights[1], np.zeros(num_class)), axis=0)
weights[0] = np.concatenate((weights[0], -0.0001 * np.random.random_sample((shape, num_class)) 0.0001), axis=1)
# Deleting the old dense output layer
model.layers.pop()
# get the output layers
a = model.get_layer("a").output
b = model.get_layer("b").output
c = model.get_layer('c').output
# Replace dense output layer (x)
out = layers.Dense(new_num_class, name='fc1', use_bias=True)(c)
model = models.Model(inputs=model.input, outputs=[c, b, a, out])
# set weights to the layer
model.get_layer('fc1').set_weights(weights)
return model
轉載請註明出處，本文鏈接：https://www.uj5u.com/shujuku/442730.html