时间戳

首页 > 解决方案 > 如何使用预训练模型进行双输入迁移学习

python - 如何使用预训练模型进行双输入迁移学习

问题描述

我将使用预训练模型（之前使用save_best_only的参数保存ModelCheckpoint ）进行双输入迁移学习。我有以下内容：

pretrained_model = load_model('best_weight.h5')

def combined_net(): 
    
    u_model = pretrained_model
    u_output = u_model.layers[-1].output
    
    v_model = pretrained_model
    v_output = v_model.layers[-1].output


    concat = concatenate([u_output, v_output])
    #hidden1 = Dense(64, activation=activation)(concat) #was 128
    main_output = Dense(1, activation='sigmoid', name='main_output')(concat) # pretrained_model.get_layer("input_1").input

    model = Model(inputs=[u_model.input, v_model.input], outputs=main_output)
    opt = SGD(lr=0.001, nesterov=True)
    model.compile(loss='binary_crossentropy', optimizer=opt, metrics=['accuracy'])
    return model

当我尝试使用时：

best_weights_file="weights_best_of_pretrained_dual.hdf5"
checkpoint = ModelCheckpoint(best_weights_file, monitor='val_acc', verbose=1, save_best_only=True, mode='max')
callbacks = [checkpoint]

base_model = combined_net()
print(base_model.summary)

history = base_model.fit([x_train_u, x_train_v], y_train,
                         batch_size=batch_size,
                         epochs=epochs,
                         callbacks=callbacks, 
                         verbose=1,
                         validation_data=([x_test_u, x_test_v], y_test), 
                         shuffle=True)

我有以下错误：

ValueError: The list of inputs passed to the model is redundant. All inputs should only appear once. Found: [<tf.Tensor 'input_1_5:0' shape=(None, None, None, 3) dtype=float32>, <tf.Tensor 'input_1_5:0' shape=(None, None, None, 3) dtype=float32>]

显然，model = Model(inputs=[u_model.input, v_model.input], outputs=main_output)line 似乎会导致错误。

我要做的就是使用预训练模型（“best_weight.h5”）进行双输入到单输出模型。两个输入都与先前初始化的相同，并且该concatenate层应连接加载模型构建的每个模型的最后一层之前的层。

我尝试了几种在网上找到的方法，但无法正确设置模型。

我希望有人能帮助我

编辑：

预训练模型如下图所示：

def vgg_16():
    b_model = VGG16(weights='imagenet', include_top=False)
    x = b_model.output
    x = GlobalAveragePooling2D()(x)
    x = Dense(256, activation=activation)(x)
    predictions = Dense(1, activation='sigmoid')(x)
    model = Model(inputs=b_model.input, outputs=predictions)
    for layer in model.layers[:15]:  #
        layer.trainable = False
    opt = SGD(lr=init_lr, nesterov=True)
    model.compile(loss='binary_crossentropy', optimizer=opt, metrics=['accuracy'])
    return model

main_model = vgg_16()
history = main_model.fit(X_train, y_train, batch_size=batch_size, 
          epochs=EPOCHS, validation_data=(X_test, y_test), verbose=1, 
          callbacks=[es, mc, l_r])

标签： pythontensorflowmachine-learningkerasdeep-learning

解决方案

这里是正确的方法。当我定义时，combined_net我定义了 2 个新输入，它们用于以pre_trained相同的方式为模型提供数据

def vgg_16():
    
    b_model = tf.keras.applications.VGG16(weights='imagenet', include_top=False)
    x = b_model.output
    x = GlobalAveragePooling2D()(x)
    x = Dense(256, activation='relu')(x)
    predictions = Dense(1, activation='sigmoid')(x)
    model = Model(inputs=b_model.input, outputs=predictions)
    
    for layer in model.layers[:15]:
        layer.trainable = False
        
    opt = SGD(lr=0.003, nesterov=True)
    model.compile(loss='binary_crossentropy', optimizer=opt, metrics=['accuracy'])
    
    return model

main_model = vgg_16()
# main_model.fit(...)

pretrained_model = Model(main_model.input, main_model.layers[-2].output)

def combined_net(): 
    
    inp_u = Input((224,224,3)) # the same input dim of pretrained_model
    inp_v = Input((224,224,3)) # the same input dim of pretrained_model
    
    u_output = pretrained_model(inp_u)
    v_output = pretrained_model(inp_v)


    concat = concatenate([u_output, v_output])
    main_output = Dense(1, activation='sigmoid', name='main_output')(concat)

    model = Model(inputs=[inp_u, inp_v], outputs=main_output)
    opt = SGD(lr=0.001, nesterov=True)
    model.compile(loss='binary_crossentropy', optimizer=opt, metrics=['accuracy'])
    return model

base_model = combined_net()
base_model.summary()

推荐阅读