/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 vote209 views1 answer
Python lvl up
Python
0 vote241 views1 answer
Import ArraField django
Python
1 vote211 views1 answer
Python check if input() gives error
Python
4 votes245 views3 answers
ArrayField in Django
Python Django
0 vote219 views1 answer
Python - caéculate the average based on the level of a second column in a df
Python
0 vote224 views2 answers
Which columns has null data?
Python
0 vote219 views1 answer
Difference between this and super
Python
1 vote212 views1 answer
Django model query join
Python
-1 vote247 views1 answer
PyPDF2 Python PDF
Python
0 vote237 views1 answer
New column with addition of other columns
Python