What is the difference between model.get_layer() and model.get_layer().output

user_14542608 0
Viewed 878

I know this is silly question but I am little bit confused here... for I am using transfer learning using VGG16 and it has a layer named 'block4_pool'. so what is the difference between the objects these two lines returns,

base_model.get_layer('block4_pool')
base_model.get_layer('block4_pool').output

what are they returning?

transfer-learning keras tensorflow computer-vision machine-learning
2 Answers
base_model.get_layer('block4_pool')

Retrieves the layer named block4_pool which is a tensorflow.keras.layers object

base_model.get_layer('block4_pool').output

Retrieves the output tensor(s) of the layer named block4_pool.

user_45746330

The first one returns a layer object which is a MaxPooling2D layer.

The second one is the output tensor of this layer.

let's see what is exactly these are:

First statement:

print(base_model.get_layer('block4_pool'))

>>  <tensorflow.python.keras.layers.pooling.MaxPooling2D object at 0x7f50fe7f8ed0>

Second statement:

print(base_model.get_layer('block4_pool').output) 

>>  KerasTensor(type_spec=TensorSpec(shape=(None, 9, 9, 512), dtype=tf.float32, name=None), name='block4_pool/MaxPool:0', description="created by layer 'block4_pool'")
user_24232780
Related