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

1 vote335 views1 answer
No handles with labels found to put in legend
Python
17 votes338 views2 answers
Make password python
Python
0 vote328 views4 answers
Pandas replace word begins with contains
Python
5 votes314 views4 answers
Ask a question on python
Python
0 vote346 views1 answer
Fcn tensorflow
Python
0 vote342 views1 answer
Minio python make an object
Python
0 vote323 views2 answers
Python code for create diamond shape with integer
Python
0 vote319 views1 answer
Bag of word scikit learn
Python
0 vote327 views1 answer
Tuple comparison python
Python
0 vote347 views1 answer
Learn basic facts about dataframe | dataframe info
Python