[开发技巧]·keras如何冻结网络层

在使用keras进行进行finetune有时需要冻结一些网络层加速训练

keras中提供冻结单个层的方法：layer.trainable = False

这个应该如何使用？下面给大家一些例子

1.冻结model所有网络层

base_model = DenseNet121(include_top=False, weights="imagenet",input_shape=(224, 224, 3))

for layer in base_model.layers:

layer.trainable = False

2.冻结model某些网络层

在keras中除了从model.layers取得layer，我们还可以通过model.get_layer(layer_name)获取。

base_model = VGG19(weights='imagenet')

base_model.get_layer('block4_pool').trainable = False

你可能会疑问，我不知道layer_name该怎么办呢？答案是通过model.summary()输出一下，

如下所示，最左面一列就是layer_name(注意是括号外面的>

__________________________________________________________________________________________________

Layer (type) Output Shape Param # Connected to

==================================================================================================

input_1 (InputLayer) (None, 224, 224, 3) 0

__________________________________________________________________________________________________

NASNet (Model) (None, 7, 7, 1056) 4269716 input_1[0][0]

__________________________________________________________________________________________________

resnet50 (Model) (None, 7, 7, 2048) 23587712 input_1[0][0]

__________________________________________________________________________________________________

densenet121 (Model) (None, 7, 7, 1024) 7037504 input_1[0][0]

__________________________________________________________________________________________________

global_average_pooling2d_1 (Glo (None, 1056) 0 NASNet[1][0]

__________________________________________________________________________________________________

global_average_pooling2d_2 (Glo (None, 2048) 0 resnet50[1][0]

__________________________________________________________________________________________________

global_average_pooling2d_3 (Glo (None, 1024) 0 densenet121[1][0]

__________________________________________________________________________________________________

concatenate_5 (Concatenate) (None, 4128) 0 global_average_pooling2d_1[0][0]

global_average_pooling2d_2[0][0]

global_average_pooling2d_3[0][0]

__________________________________________________________________________________________________

dropout_1 (Dropout) (None, 4128) 0 concatenate_5[0][0]

__________________________________________________________________________________________________

classifier (Dense) (None, 200) 825800 dropout_1[0][0]

==================================================================================================

Total params: 35,720,732

Trainable params: 825,800

Non-trainable params: 34,894,932

__________________________________________________________________________________________________

None

hope this helps

本文同步分享在 博客“小宋是呢”(CSDN)。

如有侵权，请联系 support@oschina.cn 删除。

本文参与“OSC源创计划”，欢迎正在阅读的你也加入，一起分享。