多尺度CNN - Keras实现

Question

我想用python实现一个多尺度CNN。我的目标是为三个不同的尺度使用三个不同的cnn，并将最终层的最终输出连接起来，并将它们馈送到FC层以获得输出预测。

但是我不明白我怎么才能实现这个。我知道如何实现单尺度CNN。

有谁能帮我一下吗?

Answer 1

我不明白为什么要有3个CNN，因为大多数情况下你会得到和一个CNN相同的结果。也许你可以训练得快一点。也许你也可以做池和一些重发操作(我猜这可能证明类似于你想要的)。

然而，对于每个CNN，你需要一个成本函数来优化你使用的"启发式"(例如:提高识别)。此外，你可以在NN风格转移中做一些事情，其中你比较几个"目标"(内容和风格矩阵)之间的结果;或者简单地训练3个cnn，然后切断最后一层(或冻结它们)，用已经训练过的权重再次训练，但现在是你的目标FN层…

Answer 2

这是一个多输入CNN的例子。您只需要引用提供每个网络输出的变量。然后使用concatate并将它们传递到一个密集的网络或任何你喜欢的任务。

def multires_CNN(filters, kernel_size, multires_data):
    '''uses Functional API for Keras 2.x support.
       multires data is output from load_standardized_multires()
    '''
    input_fullres = Input(multires_data[0].shape[1:], name = 'input_fullres')
    fullres_branch = Conv2D(filters, (kernel_size, kernel_size),
                     activation = LeakyReLU())(input_fullres)
    fullres_branch = MaxPooling2D(pool_size = (2,2))(fullres_branch)
    fullres_branch = BatchNormalization()(fullres_branch)
    fullres_branch = Flatten()(fullres_branch)
    input_medres = Input(multires_data[1].shape[1:], name = 'input_medres')
    medres_branch = Conv2D(filters, (kernel_size, kernel_size),
                     activation=LeakyReLU())(input_medres)
    medres_branch = MaxPooling2D(pool_size = (2,2))(medres_branch)
    medres_branch = BatchNormalization()(medres_branch)
    medres_branch = Flatten()(medres_branch)
    input_lowres = Input(multires_data[2].shape[1:], name = 'input_lowres')
    lowres_branch = Conv2D(filters, (kernel_size, kernel_size),
                     activation = LeakyReLU())(input_lowres)
    lowres_branch = MaxPooling2D(pool_size = (2,2))(lowres_branch)
    lowres_branch = BatchNormalization()(lowres_branch)
    lowres_branch = Flatten()(lowres_branch)
    merged_branches = concatenate([fullres_branch, medres_branch, lowres_branch])
    merged_branches = Dense(128, activation=LeakyReLU())(merged_branches)
    merged_branches = Dropout(0.5)(merged_branches)
    merged_branches = Dense(2,activation='linear')(merged_branches)
    model = Model(inputs=[input_fullres, input_medres ,input_lowres],
                  outputs=[merged_branches])
    model.compile(loss='mean_absolute_error', optimizer='adam')
    return model