/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 vote258 views2 answers
Aminul
Python
0 vote256 views1 answer
Generate python date list
Python
2 votes299 views2 answers
Django filter and condition
Python Django
1 vote275 views1 answer
_set in django
Python
3 votes300 views2 answers
Python iterate over string
Python
0 vote253 views1 answer
Python - change the bin size of an histogram+
Python
0 vote217 views1 answer
Zip used in python stack overflow
Python
1 vote288 views2 answers
Between date pandas
Python
16 votes256 views4 answers
Sort tuple list python
Python
-2 votes251 views1 answer
How to check if a string contains spaces in python
Python