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

31 votes322 views3 answers
Python get names of columns
Python
0 vote367 views1 answer
Pycharm shortcut to create methos
Python
0 vote335 views1 answer
Lsit append in python
Python
0 vote328 views4 answers
Pandas filter
Python
0 vote325 views0 answer
Python
8 votes375 views6 answers
AttributeError: type object 'datetime.datetime' has no attribute 'datetime'
Python
3 votes318 views1 answer
Python remove non letters from string
Python
0 vote337 views1 answer
Django MESSAGE_TAGS
Python Django
78 votes336 views6 answers
Wait in python
Python
1 vote334 views2 answers
Change xticks python
Python