我目前正在嘗試使用名稱為自定義激活的多個(gè)圖層cust_sig。但是當(dāng)我嘗試編譯模型時(shí)，我得到一個(gè) ValueError ，因?yàn)槎鄠€(gè)層具有相同的 name cust_sig。我知道我可以手動(dòng)更改每個(gè)圖層的名稱，但想知道是否可以_1, _2, ...像對(duì)內(nèi)置圖層一樣自動(dòng)添加到名稱中。可以在下面找到模型定義。# Creating a modelfrom tensorflow.python.keras import kerasfrom tensorflow.python.keras.models import Modelfrom tensorflow.python.keras.layers import Dense# Custom activation functionfrom tensorflow.python.keras.layers import Activationfrom tensorflow.python.keras import backend as Kfrom keras.utils.generic_utils import get_custom_objectsdef custom_activation(x): return (K.sigmoid(x) * 5) - 1get_custom_objects().update({'custom_activation': Activation(custom_activation)})data_format = 'channels_first'spec_input = keras.layers.Input(shape=(1, 3, 256), name='spec')x = keras.layers.Flatten(data_format)(spec_input)for layer in range(3): x = Dense(512)(x) x = Activation('custom_activation', name='cust_sig')(x)out = Dense(256, activation="sigmoid", name='out')(x)model = Model(inputs=spec_input, outputs=out)錯(cuò)誤信息如下所示Traceback (most recent call last): File "/home/xyz/anaconda3/envs/ctf/lib/python3.7/site-packages/tensorflow/python/training/tracking/base.py", line 457, in _method_wrapper result = method(self, *args, **kwargs) File "/home/xyz/anaconda3/envs/ctf/lib/python3.7/site-packages/tensorflow/python/keras/engine/network.py", line 315, in _init_graph_network self.inputs, self.outputs) File "/home/xyz/anaconda3/envs/ctf/lib/python3.7/site-packages/tensorflow/python/keras/engine/network.py", line 1861, in _map_graph_network str(all_names.count(name)) + ' times in the model. 'ValueError: The name "cust_sig" is used 3 times in the model. All layer names should be unique.
3 回答
嗶嗶one
TA貢獻(xiàn)1854條經(jīng)驗(yàn) 獲得超8個(gè)贊
下面應(yīng)該做：
def custom_activation(x):
return (K.sigmoid(x) * 5) - 1
class CustSig(Layer):
def __init__(self, my_activation, **kwargs):
super(CustSig, self).__init__(**kwargs)
self.supports_masking = True
self.activation = my_activation
def call(self, inputs):
return self.activation(inputs)
def get_config(self):
config = {'activation': activations.serialize(self.activation)}
base_config = super(Activation, self).get_config()
return dict(list(base_config.items()) + list(config.items()))
def compute_output_shape(self, input_shape):
return input_shape
說明：
從源代碼來看，自動(dòng)命名的工作原理如下：
if not name:
self._name = backend.unique_object_name(
generic_utils.to_snake_case(self.__class__.__name__),
zero_based=zero_based)
else:
self._name = name
檢查 Keras 圖是否存在與您定義的對(duì)象同名的對(duì)象 - 如果存在，則繼續(xù)遞增 1，直到?jīng)]有匹配項(xiàng)。問題是，您不能指定name=，因?yàn)檫@消除了上述條件的自動(dòng)命名。
唯一的解決方法可能是使用所需的名稱作為類名定義您自己的自定義激活層，如上所示，其表現(xiàn)如下：
ipt = Input(shape=(1, 3, 256), name='spec')
x = Flatten('channels_last')(ipt)
for _ in range(3):
x = Dense(512)(x)
x = CustSig(custom_activation)(x)
out = Dense(256, activation='sigmoid', name='out')(x)
model = Model(ipt, out)
print(model.layers[3].name)
print(model.layers[5].name)
print(model.layers[7].name)
cust_sig
cust_sig_1
cust_sig_2
ITMISS
TA貢獻(xiàn)1871條經(jīng)驗(yàn) 獲得超8個(gè)贊
如果您查看Layerclass的源代碼，您可以找到?jīng)Q定層名稱的這些行。
if not name:
prefix = self.__class__.__name__
name = _to_snake_case(prefix) + '_' + str(K.get_uid(prefix))
self.name = name
K.get_uid(prefix)將從圖中獲取唯一 ID，這就是您看到activation_1,的原因activation_2。
如果你想對(duì)你的自定義激活函數(shù)有同樣的效果，更好的方法是定義你自己的繼承自Layer.
class MyAct(Layer):
def __init__(self):
super().__init__()
def call(self, inputs):
return (K.sigmoid(inputs) * 5) - 1
spec_input = Input(shape=(10,10))
x = Flatten()(spec_input)
for layer in range(3):
x = Dense(512)(x)
x = MyAct()(x)
model = Model(spec_input, x)
model.summary()
輸出
# Layer (type) Output Shape Param #
# =================================================================
# input_1 (InputLayer) (None, 10, 10) 0
# _________________________________________________________________
# flatten_1 (Flatten) (None, 100) 0
# _________________________________________________________________
# dense_1 (Dense) (None, 512) 51712
# _________________________________________________________________
# my_act_1 (MyAct) (None, 512) 0
# _________________________________________________________________
# dense_2 (Dense) (None, 512) 262656
# _________________________________________________________________
# my_act_2 (MyAct) (None, 512) 0
# _________________________________________________________________
# dense_3 (Dense) (None, 512) 262656
# _________________________________________________________________
# my_act_3 (MyAct) (None, 512) 0
# =================================================================
# Total params: 577,024
# Trainable params: 577,024
# Non-trainable params: 0
紅顏莎娜
TA貢獻(xiàn)1842條經(jīng)驗(yàn) 獲得超13個(gè)贊
如果要specific_name多次使用數(shù)字后綴，請(qǐng)使用以下命令：
tf.get_default_graph().unique_name("specific_name")
或者
tf.compat.v1.get_default_graph().unique_name("specific_name")
在你的情況下：
...
for layer in range(3):
x = Dense(512)(x)
x = Activation('custom_activation', name=tf.get_default_graph().unique_name("cust_sig"))(x)
...
添加回答
舉報(bào)
0/150
提交
取消