/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 vote288 views1 answer
2 liste to a dictionary
Python
0 vote318 views1 answer
Mysql pyzo
Python
0 vote317 views1 answer
Proper pagination django template
Python
0 vote326 views1 answer
Apply dictionary to df clumn
Python
1 vote313 views1 answer
Remove the Unnamed column in pandas
Python
0 vote309 views1 answer
Python die
Python
0 vote303 views1 answer
How to add values in python
Python
0 vote343 views1 answer
How to for loop length print in python
Python
0 vote317 views1 answer
Raspistill timelapse
Python
0 vote372 views3 answers
How to create a User and User profile in django rest framework
Python