/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

5 votes318 views2 answers
How to plot pie chart in python
Python
0 vote200 views1 answer
Class has no object members
Python
8 votes237 views4 answers
Create an array with same value python
Python
3 votes222 views1 answer
Factorial program
Python
1 vote248 views1 answer
Numpy dot product
Python
0 vote229 views1 answer
Obtenir coordonnees souris python
Python
0 vote224 views1 answer
Char count in python
Python
0 vote237 views1 answer
Dump ML Model
Python
2 votes247 views2 answers
How to change colour of rows in csv using pandas
Python
1 vote257 views1 answer
Yesno django
Python Django