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

7 votes133 views3 answers
Python set cwd to file location
Python
1 vote157 views1 answer
Django.db.models avg
Python Django
0 vote128 views2 answers
Python defualt error handler
Python
0 vote112 views1 answer
Python resample time series
Python
7 votes129 views2 answers
"How to get the remainder of a number when dividing in python"
Python
0 vote126 views1 answer
Macos youtube-dl unable to get local issuer certificate _ssl.c:1131
Python
0 vote132 views1 answer
Torch split classes stratified
Python
0 vote122 views1 answer
Unable to import flask pylint
Python
0 vote123 views1 answer
Run for loop inside pdb
Python
0 vote86 views1 answer
Divide array into equal parts/slices python
Python