Keras transfer learning

inputs = keras.Input(shape=(150, 150, 3))
# We make sure that the base_model is running in inference mode here,
# by passing `training=False`. This is important for fine-tuning, as you will
# learn in a few paragraphs.
x = base_model(inputs, training=False)
# Convert features of shape `base_model.output_shape[1:]` to vectors
# Use golbal averaging pool instead of flatten in some cases
x = keras.layers.GlobalAveragePooling2D()(x)
# A Dense classifier with a single unit (binary classification)
outputs = keras.layers.Dense(1)(x)
model = keras.Model(inputs, outputs)

Source: keras.io

Similar codes

6 votes213 views1 answer
Django desc order
Python Django
0 vote151 views1 answer
.comments.all order django
Python
16 votes144 views4 answers
Python check list contains another list
Python
38 votes140 views4 answers
Python color text console
Python
1 vote163 views2 answers
How to print values without space in python
Python
0 vote154 views1 answer
How to redirect where requests library downloads file python
Python
89 votes161 views6 answers
Requirements.txt python
Python
0 vote155 views2 answers
Python3 ngrok.py
Python
0 vote180 views1 answer
Django not migrating
Python Django
-2 votes167 views9 answers
Django
Python