Question

我训练了一个模型，并希望使用功能性api将其与另一个keras模型相结合（后端是tensorflow版本1.4）

我的第一个模型如下：

import tensorflow.contrib.keras.api.keras as keras

model = keras.models.Sequential()
input = Input(shape=(200,))
dnn = Dense(400, activation="relu")(input)
dnn = Dense(400, activation="relu")(dnn)
output = Dense(5, activation="softmax")(dnn)
model = keras.models.Model(inputs=input, outputs=output)

在我训练这个模型后，我使用keras model.save（）方法保存它。我也可以加载模型并重新训练它。

现在我想使用此模型的输出作为第二个模型的附加输入：

# load first model
old_model = keras.models.load_model(path_to_old_model)

input_1 = Input(shape=(200,))
input_2 = Input(shape=(200,))
output_old_model = old_model(input_2)

merge_layer = concatenate([input_1, output_old_model])
dnn_layer = Dense(200, activation="relu")(merge_layer)
dnn_layer = Dense(200, activation="relu")(dnn_layer)
output = Dense(10, activation="sigmoid")(dnn_layer)
new_model = keras.models.Model(inputs=[input_1, input_2], outputs=output)
new_model.compile(loss="binary_crossentropy", optimizer="adam", metrics=["accuracy"]
new_model.fit(inputs=[x1,x2], labels=labels, epochs=50, batch_size=32)

当我尝试这个时，我收到以下错误消息：

FailedPreconditionError (see above for traceback): Attempting to use uninitialized value dense_1/kernel
 [[Node: dense_1/kernel/read = Identity[T=DT_FLOAT, _class=["loc:@dense_1/kernel"], _device="/job:localhost/replica:0/task:0/device:GPU:0"](dense_1/kernel)]]
 [[Node: model_1_1/dense_3/BiasAdd/_79 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/device:CPU:0", send_device="/job:localhost/replica:0/task:0/device:GPU:0", send_device_incarnation=1, tensor_name="edge_68_model_1_1/dense_3/BiasAdd", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"]()]]

Answer 1

我会按照以下步骤执行此操作：

定义用于构建具有相同架构的干净模型的函数：

def build_base():
    input = Input(shape=(200,))
    dnn = Dense(400, activation="relu")(input)
    dnn = Dense(400, activation="relu")(dnn)
    output = Dense(5, activation="softmax")(dnn)
    model = keras.models.Model(inputs=input, outputs=output)
    return input, output, model

构建同一型号的两个副本：

input_1, output_1, model_1 = build_base()
input_2, output_2, model_2 = build_base()

在两个模型中设置权重：

model_1.set_weights(old_model.get_weights())
model_2.set_weights(old_model.get_weights())

现在做其余的事情：

merge_layer = concatenate([input_1, output_2])
dnn_layer = Dense(200, activation="relu")(merge_layer)
dnn_layer = Dense(200, activation="relu")(dnn_layer)
output = Dense(10, activation="sigmoid")(dnn_layer)
new_model = keras.models.Model(inputs=[input_1, input_2], outputs=output)

Answer 2

假设您有一个称为pretrained_model的经过预先训练/保存的CNN模型，并且想要向其添加紧密连接的层，然后使用功能性API可以编写如下内容：

from keras import models, layers

kmodel = layers.Flatten()(pretrained_model.output)
kmodel = layers.Dense(256, activation='relu')(kmodel)
kmodel_out = layers.Dense(1, activation='sigmoid')(kmodel)
model = models.Model(pretrained_model.input, kmodel_out)

keras结合了预训练模型

2 个答案: