/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 vote353 views1 answer
Dimension of an indez pandas
Python
4 votes313 views3 answers
Dice simulator python
Python
0 vote299 views1 answer
Pandas loc index not in
Python
0 vote323 views1 answer
Dict itterator python recursive
Python
0 vote340 views1 answer
Time a line of code python
Python
1 vote391 views2 answers
Python nltk tokenize
Python
0 vote319 views1 answer
Find and flag duplicates pandas
Python
0 vote324 views1 answer
Python placeholder
Python
0 vote332 views2 answers
How to terminate a program cv2 python
Python
0 vote308 views2 answers
Pandas agg rename columns
Python