如何在 Keras 中获取图层的类型？

Question

我正在尝试为给定（通用）模型选择最后一个 Conv2D 层。model.summary()提供了一个图层列表及其类型，但如何访问它以找到该类型的图层？

输出model.summary()：

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

Answer 1

我想你要找的是这个：

layer.__class__.__name__

图层所在的位置

model.layers

Answer 2

您可以按model.layers相反顺序迭代并通过以下方式检查图层类型isinstance：

next(x for x in model.layers[::-1] if isinstance(x, keras.layers.Conv2D))