Eka*_*Eka 38 python theano keras keras-layer
我正在努力做转学习; 为此我想删除神经网络的最后两层并添加另外两层.这是一个示例代码,它也输出相同的错误.
from keras.models import Sequential
from keras.layers import Input,Flatten
from keras.layers.convolutional import Convolution2D, MaxPooling2D
from keras.layers.core import Dropout, Activation
from keras.layers.pooling import GlobalAveragePooling2D
from keras.models import Model
in_img = Input(shape=(3, 32, 32))
x = Convolution2D(12, 3, 3, subsample=(2, 2), border_mode='valid', name='conv1')(in_img)
x = Activation('relu', name='relu_conv1')(x)
x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), name='pool1')(x)
x = Convolution2D(3, 1, 1, border_mode='valid', name='conv2')(x)
x = Activation('relu', name='relu_conv2')(x)
x = GlobalAveragePooling2D()(x)
o = Activation('softmax', name='loss')(x)
model = Model(input=in_img, output=[o])
model.compile(loss="categorical_crossentropy", optimizer="adam")
#model.load_weights('model_weights.h5', by_name=True)
model.summary()
model.layers.pop()
model.layers.pop()
model.summary()
model.add(MaxPooling2D())
model.add(Activation('sigmoid', name='loss'))
Run Code Online (Sandbox Code Playgroud)
我删除了图层pop()
但是当我尝试添加它输出此错误时
AttributeError:'Model'对象没有属性'add'
我知道错误最可能的原因是使用不当model.add()
.我应该使用什么其他语法?
编辑:
我试图在keras中删除/添加图层但是在加载外部权重后不允许添加它.
from keras.models import Sequential
from keras.layers import Input,Flatten
from keras.layers.convolutional import Convolution2D, MaxPooling2D
from keras.layers.core import Dropout, Activation
from keras.layers.pooling import GlobalAveragePooling2D
from keras.models import Model
in_img = Input(shape=(3, 32, 32))
def gen_model():
in_img = Input(shape=(3, 32, 32))
x = Convolution2D(12, 3, 3, subsample=(2, 2), border_mode='valid', name='conv1')(in_img)
x = Activation('relu', name='relu_conv1')(x)
x = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), name='pool1')(x)
x = Convolution2D(3, 1, 1, border_mode='valid', name='conv2')(x)
x = Activation('relu', name='relu_conv2')(x)
x = GlobalAveragePooling2D()(x)
o = Activation('softmax', name='loss')(x)
model = Model(input=in_img, output=[o])
return model
#parent model
model=gen_model()
model.compile(loss="categorical_crossentropy", optimizer="adam")
model.summary()
#saving model weights
model.save('model_weights.h5')
#loading weights to second model
model2=gen_model()
model2.compile(loss="categorical_crossentropy", optimizer="adam")
model2.load_weights('model_weights.h5', by_name=True)
model2.layers.pop()
model2.layers.pop()
model2.summary()
#editing layers in the second model and saving as third model
x = MaxPooling2D()(model2.layers[-1].output)
o = Activation('sigmoid', name='loss')(x)
model3 = Model(input=in_img, output=[o])
Run Code Online (Sandbox Code Playgroud)
它显示此错误
RuntimeError: Graph disconnected: cannot obtain value for tensor input_4 at layer "input_4". The following previous layers were accessed without issue: []
Run Code Online (Sandbox Code Playgroud)
ind*_*you 49
您可以使用output
最后一个模型并创建一个新模型.较低的层保持不变.
model.summary()
model.layers.pop()
model.layers.pop()
model.summary()
x = MaxPooling2D()(model.layers[-1].output)
o = Activation('sigmoid', name='loss')(x)
model2 = Model(input=in_img, output=[o])
model2.summary()
Run Code Online (Sandbox Code Playgroud)
检查如何使用keras.applications中的模型进行转移学习?
编辑更新:
新错误是因为您正在尝试在全局上创建新模型,in_img
而该模型实际上并未在先前的模型创建中使用..您实际上是在定义本地模型in_img
.因此,全局in_img
显然没有连接到符号图中的上层.它与加载重量无关.
为了更好地解决此问题,您应该使用model.input
引用输入.
model3 = Model(input=model2.input, output=[o])
Yam*_*eko 26
从 Keras 2.3.1 和 TensorFlow 2.0 开始,model.layers.pop()
无法按预期工作(请参阅此处的问题)。他们提出了两种选择来做到这一点。
一种选择是重新创建模型并复制图层。例如,如果您想删除最后一层并添加另一层,您可以执行以下操作:
model = Sequential()
for layer in source_model.layers[:-1]: # go through until last layer
model.add(layer)
model.add(Dense(3, activation='softmax'))
model.summary()
model.compile(optimizer='adam', loss='categorical_crossentropy')
Run Code Online (Sandbox Code Playgroud)
另一种选择是使用功能模型:
predictions = Dense(3, activation='softmax')(source_model.layers[-2].output)
model = Model(inputs=inputs, outputs=predictions)
model.compile(optimizer='adam', loss='categorical_crossentropy')
Run Code Online (Sandbox Code Playgroud)
model.layers[-1].output
表示最后一层的输出,即最终输出,因此在您的代码中,您实际上没有删除任何层,而是添加了另一个头部/路径。
Wes*_* Na 11
另一种方式
from keras.models import Model
layer_name = 'relu_conv2'
model2= Model(inputs=model1.input, outputs=model1.get_layer(layer_name).output)
Run Code Online (Sandbox Code Playgroud)
小智 11
Wesam Na 答案的另一种选择,如果您不知道图层名称,您可以通过以下方式简单地切断最后一层:
from keras.models import Model
model2= Model(inputs=model1.input, outputs=model1.layers[-2].output)
Run Code Online (Sandbox Code Playgroud)
归档时间: |
|
查看次数: |
36170 次 |
最近记录: |