Skip to main content
 首页 » 编程设计

python之Keras:如何连接两个 CNN

2025年02月15日8unruledboy

我正在尝试实现本文中的 CNN 模型 (https://arxiv.org/abs/1605.07333)

在这里,它们有两个不同的上下文作为输入,由两个独立的 conv 和 max-pooling 层处理。汇集后,他们将结果合并。

假设每个 CNN 都是这样建模的,我如何实现上述模型?

def baseline_cnn(activation='relu'): 
 
model = Sequential() 
model.add(Embedding(SAMPLE_SIZE, EMBEDDING_DIMS, input_length=MAX_SMI_LEN)) 
model.add(Dropout(0.2)) 
model.add(Conv1D(NUM_FILTERS, FILTER_LENGTH, padding='valid', activation=activation, strides=1)) 
model.add(GlobalMaxPooling1D()) 
model.add(Dense(1)) 
model.add(Activation('sigmoid')) 
model.compile(loss='binary_crossentropy', optimizer='adam',  metrics=['accuracy']) 
 
return model 

提前致谢!

最终代码:我只是使用@FernandoOrtega 的解决方案:

def build_combined(FLAGS, NUM_FILTERS, FILTER_LENGTH1, FILTER_LENGTH2): 
    Dinput = Input(shape=(FLAGS.max_dlen, FLAGS.dset_size)) 
    Tinput = Input(shape=(FLAGS.max_tlen, FLAGS.tset_size)) 
 
 
    encode_d= Conv1D(filters=NUM_FILTERS, kernel_size=FILTER_LENGTH1,  activation='relu', padding='valid',  strides=1)(Dinput) 
    encode_d = Conv1D(filters=NUM_FILTERS*2, kernel_size=FILTER_LENGTH1,  activation='relu', padding='valid',  strides=1)(encode_d) 
    encode_d = GlobalMaxPooling1D()(encode_d) 
 
    encode_tt = Conv1D(filters=NUM_FILTERS, kernel_size=FILTER_LENGTH2,  activation='relu', padding='valid',  strides=1)(Tinput) 
    encode_tt = Conv1D(filters=NUM_FILTERS*2, kernel_size=FILTER_LENGTH1,  activation='relu', padding='valid',  strides=1)(encode_tt) 
    encode_tt = GlobalMaxPooling1D()(encode_tt) 
 
    encode_combined = keras.layers.concatenate([encode_d, encode_tt]) 
 
 
    # Fully connected  
    FC1 = Dense(1024, activation='relu')(encode_combined) 
    FC2 = Dropout(0.1)(FC1) 
    FC2 = Dense(512, activation='relu')(FC2) 
 
    predictions = Dense(1, kernel_initializer='normal')(FC2)  
 
    combinedModel = Model(inputs=[Dinput, Tinput], outputs=[predictions]) 
    combinedModel.compile(optimizer='adam', loss='mean_squared_error', metrics=[accuracy]) 
 
    print(combinedModel.summary()) 
 
    return combinedModel 

请您参考如下方法:

如果你想连接两个子网络,你应该使用 keras.layer.concatenate 功能。

此外,我建议您应该使用 Functional API,只要它最容易设计像您这样的复杂网络。例如:

def baseline_cnn(activation='relu') 
 
    # Defining input 1 
    input1 = Embedding(SAMPLE_SIZE, EMBEDDING_DIMS, input_length=MAX_SMI_LEN) 
    x1 = Dropout(0.2)(input) 
    x1 = Conv1D(NUM_FILTERS, FILTER_LENGTH, padding='valid', activation=activation, strides=1)(x1) 
    x1 = GlobalMaxPooling1D()(x1) 
 
    # Defining input 2 
    input2 = Embedding(SAMPLE_SIZE, EMBEDDING_DIMS, input_length=MAX_SMI_LEN) 
    x2 = Dropout(0.2)(input) 
    x2 = Conv1D(NUM_FILTERS, FILTER_LENGTH, padding='valid', activation=activation, strides=1)(x2) 
    x2 = GlobalMaxPooling1D()(x2) 
 
    # Merging subnetworks 
    x = concatenate([input1, input2]) 
 
    # Final Dense layer and compilation 
    x = Dense(1, activation='sigmoid') 
    model = Model(inputs=[input1, input2], x) 
    model.compile(loss='binary_crossentropy', optimizer='adam',  metrics=['accuracy']) 
 
return model 

编译此模型后,您可以通过 model.fit([data_split1, data_split2]) 对其进行拟合/评估,其中 data_split1 和 data_split2 是您作为输入的不同上下文。

Keras 文档中有关多输入的更多信息:Multi-input and multi-output models .