/Python/Learningrate scheduler tensorflow

Learningrate scheduler tensorflow

tf.keras.callbacks.LearningRateScheduler(
    schedule, verbose=0)

# This function keeps the initial learning rate for the first ten epochs
# and decreases it exponentially after that.

def scheduler(epoch, lr):
  if epoch < 10:
    return lr
  else:
    return lr * tf.math.exp(-0.1)

model = tf.keras.models.Sequential([tf.keras.layers.Dense(10)])
model.compile(tf.keras.optimizers.SGD(), loss='mse')

callback = tf.keras.callbacks.LearningRateScheduler(scheduler)
history = model.fit(np.arange(100).reshape(5, 20), np.zeros(5),
                    epochs=15, callbacks=[callback], verbose=0)

Similar codes

0 vote185 views1 answer
Transcript with timestamps in python
Python
7 votes189 views1 answer
Python xrange
Python
0 vote224 views1 answer
Production mode flask
Python Flask
3 votes186 views1 answer
Save clipboard data win32clipboard python
Python
0 vote220 views1 answer
Django save object in view
Python Django
2 votes191 views1 answer
How to make rich presence discord,py
Python
0 vote203 views1 answer
Returns all column names as a list
Python
1 vote177 views1 answer
What is serialization in django
Python
0 vote196 views2 answers
Jupyter notebook morse code francais
Python
0 vote243 views1 answer
Discord.py how to print audit logs
Python