/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

1 vote337 views1 answer
How to make a discord bot dm someone python
Python
0 vote350 views1 answer
Python yyyymmdd
Python
0 vote322 views2 answers
Remove vowels in a string python
Python
3 votes318 views2 answers
Discord.py make command admin only
Python
25 votes333 views3 answers
Store all files name in a folder python
Python
0 vote317 views1 answer
Python slack webhook
Python
5 votes319 views2 answers
Matplotlib python background color
Python
0 vote434 views1 answer
How to read multiple files in a loop in python
Python
12 votes335 views10 answers
Google
Python
3 votes353 views1 answer
Smtplib login
Python