如何解决图形已断开连接:无法获得层“ x”上的张量“ x”张量的值顺利访问了以下先前的层:[]
我正在为每个用例使用一些自定义网络框构建一个小型网络,如下所示:
def top_block(dropout = None,training = None):
# scaled input
input_1 = tf.keras.Input(shape=(1,15),dtype='float32')
input_2 = tf.keras.Input(shape=(1,dtype='float32')
if dropout:
layer_one = tf.keras.layers.Dropout(rate = dropout)(input_1,training = training)
layer_two = tf.keras.layers.Dropout(rate = dropout)(input_2,training = training)
return [layer_one,layer_two]
return [input_1,input_2]
def bottom_layer(input_layers):
data = tf.reduce_mean(input_layers,0)
cls_layer = tf.keras.layers.Dense(1,kernel_initializer = keras.initializers.glorot_uniform(seed=200),activation = 'sigmoid')(data)
model = tf.keras.Model([input_layers[0],input_layers[1]],cls_layer,name = 'model_1')
model.compile(loss = 'binary_crossentropy',optimizer = 'adam',metrics=['accuracy'])
model.summary()
return model
如果我尝试不丢失就访问该网络,则工作正常:
top_ = top_block()
model = bottom_layer(top_ )
但是如果我通过辍学进行访问,则会出现错误:
top_ = top_block(dropout = 0.2,training = True)
model = bottom_layer(top_ )
ValueError:图表已断开连接:无法在“ input_72”层获得张量Tensor(“ input_72:0”,shape =(None,1,15),dtype = float32)的值。可以顺利访问以下先前的图层:[]
- 如何访问带有辍学层的模型?
- 如何在评估期间禁用
training = False
?我需要加载完整的模型权重还是旧模型权重?
谢谢!
解决方法
我刚刚意识到我的输入来自中间层(辍学层),它应该直接来自输入层:
def top_block():
# scaled input
input_1 = tf.keras.Input(shape=(1,15),dtype='float32')
input_2 = tf.keras.Input(shape=(1,dtype='float32')
return [input_1,input_2]
def apply_dropout(layers_data,dropout_val,training):
layer_one = tf.keras.layers.Dropout(rate = dropout_val)(layers_data[0],training = training)
layer_two = tf.keras.layers.Dropout(rate = dropout_val)(layers_data[1],training = training)
return [layer_one,layer_two]
def bottom_layer(input_layers,data):
data = tf.reduce_mean(data,0)
cls_layer = tf.keras.layers.Dense(1,kernel_initializer = keras.initializers.glorot_uniform(seed=200),activation = 'sigmoid')(data)
model = tf.keras.Model(input_layers,cls_layer,name = 'model_1')
model.compile(loss = 'binary_crossentropy',optimizer = 'adam',metrics=['accuracy'])
model.summary()
return model
现在正在工作
top_ = top_block()
dropout_ = apply_dropout(top_,0.2,True)
model = bottom_layer(top_,dropout_)
版权声明:本文内容由互联网用户自发贡献,该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容, 请发送邮件至 dio@foxmail.com 举报,一经查实,本站将立刻删除。