如何在Keras中获取图层的类型?

时间:2019-07-31 13:57:44

标签: python keras

我正在尝试为给定(通用)模型选择最后一个Conv2D层。 model.summary()提供了具有其类型的图层列表,但是如何访问该列表以找到该类型的图层?

model.summary()的输出:

Layer (type)                 Output Shape              Param #   
=================================================================
input_1 (InputLayer)         (None, 224, 224, 3)       0         
_________________________________________________________________
block1_conv1 (Conv2D)        (None, 224, 224, 64)      1792      
_________________________________________________________________
...
_________________________________________________________________
predictions (Dense)          (None, 1000)              4097000   
=================================================================
Total params: 138,357,544
Trainable params: 138,357,544
Non-trainable params: 0

2 个答案:

答案 0 :(得分:4)

我认为您正在寻找的是这个

layer.__class__.__name__

图层位于

model.layers

答案 1 :(得分:2)

您可以以相反的顺序遍历ID N 1 3 2 2 3 1 并通过model.layers检查图层类型:

isinstance