Question

model = ResNet50(weights='imagenet', include_top=False, input_shape=(224, 224, 3))

上面的代码允许我使用imagenet的权重，但是我想使用自己在imagenet中设置的权重，我应该对代码进行哪些更改以使我可以训练自己数据集中的最后一层？这是我的模型的代码：

def mini_XCEPTION(input_shape, num_classes, l2_regularization=0.01):
    regularization = l2(l2_regularization)

    # base
    img_input = Input(input_shape)
    x = Conv2D(8, (3, 3), strides=(1, 1), kernel_regularizer=regularization,
               use_bias=False)(img_input)
    x = BatchNormalization()(x)
    x = Activation('relu')(x)
    x = Conv2D(8, (3, 3), strides=(1, 1), kernel_regularizer=regularization,
               use_bias=False)(x)
    x = BatchNormalization()(x)
    x = Activation('relu')(x)

    # module 1
    residual = Conv2D(16, (1, 1), strides=(2, 2),
                      padding='same', use_bias=False)(x)
    residual = BatchNormalization()(residual)

    x = SeparableConv2D(16, (3, 3), padding='same',
                        kernel_regularizer=regularization,
                        use_bias=False)(x)
    x = BatchNormalization()(x)
    x = Activation('relu')(x)
    x = SeparableConv2D(16, (3, 3), padding='same',
                        kernel_regularizer=regularization,
                        use_bias=False)(x)
    x = BatchNormalization()(x)

    x = MaxPooling2D((3, 3), strides=(2, 2), padding='same')(x)
    x = layers.add([x, residual])

    # module 2
    residual = Conv2D(32, (1, 1), strides=(2, 2),
                      padding='same', use_bias=False)(x)
    residual = BatchNormalization()(residual)

    x = SeparableConv2D(32, (3, 3), padding='same',
                        kernel_regularizer=regularization,
                        use_bias=False)(x)
    x = BatchNormalization()(x)
    x = Activation('relu')(x)
    x = SeparableConv2D(32, (3, 3), padding='same',
                        kernel_regularizer=regularization,
                        use_bias=False)(x)
    x = BatchNormalization()(x)

    x = MaxPooling2D((3, 3), strides=(2, 2), padding='same')(x)
    x = layers.add([x, residual])

    # module 3
    residual = Conv2D(64, (1, 1), strides=(2, 2),
                      padding='same', use_bias=False)(x)
    residual = BatchNormalization()(residual)

    x = SeparableConv2D(64, (3, 3), padding='same',
                        kernel_regularizer=regularization,
                        use_bias=False)(x)
    x = BatchNormalization()(x)
    x = Activation('relu')(x)
    x = SeparableConv2D(64, (3, 3), padding='same',
                        kernel_regularizer=regularization,
                        use_bias=False)(x)
    x = BatchNormalization()(x)

    x = MaxPooling2D((3, 3), strides=(2, 2), padding='same')(x)
    x = layers.add([x, residual])

    # module 4
    residual = Conv2D(128, (1, 1), strides=(2, 2),
                      padding='same', use_bias=False)(x)
    residual = BatchNormalization()(residual)

    x = SeparableConv2D(128, (3, 3), padding='same',
                        kernel_regularizer=regularization,
                        use_bias=False)(x)
    x = BatchNormalization()(x)
    x = Activation('relu')(x)
    x = SeparableConv2D(128, (3, 3), padding='same',
                        kernel_regularizer=regularization,
                        use_bias=False)(x)
    x = BatchNormalization()(x)

    x = MaxPooling2D((3, 3), strides=(2, 2), padding='same')(x)
    x = layers.add([x, residual])

    x = Conv2D(num_classes, (3, 3),
               # kernel_regularizer=regularization,
               padding='same')(x)
    x = GlobalAveragePooling2D()(x)
    output = Activation('softmax', name='predictions')(x)

    model = Model(img_input, output)
    return model

Answer 1

首先，为ResNet50加载已保存的权重。之后，您使用相同的体系结构，并在最后一层中执行以下操作：

last_layer=GlobalAveragePooling2D()(x)
last_layer.trainable=True

对于之前的所有图层，您都制作trainable=False，例如：

x = Conv2D(8, (3, 3), strides=(1, 1), kernel_regularizer=regularization,
               use_bias=False)(img_input)
x.trainable=False

residual = Conv2D(16, (1, 1), strides=(2, 2),
                      padding='same', use_bias=False)(x)
residual.trainable=False

residual = BatchNormalization()(residual)
residual.trainable=False

x = SeparableConv2D(16, (3, 3), padding='same',
                        kernel_regularizer=regularization,
                        use_bias=False)(x)
x.trainable=False

如何冻结自己模型的最后一层？

1 个答案: