/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 vote154 views1 answer
Add key if not exists python
Python
0 vote179 views1 answer
Python how to make a movement controler
Python
0 vote183 views1 answer
Rstudi matplotlib crash qt
Python
24 votes165 views3 answers
Python open link in browser
Python
9 votes169 views5 answers
Threading python
Python
0 vote163 views1 answer
Amazon redshift
Python
1 vote202 views1 answer
Django get part of queryset
Python Django
2 votes155 views2 answers
.get python
Python
-2 votes180 views1 answer
Calculate sum in 2d list python
Python
0 vote173 views1 answer
Tkinter filedialog get directory path
Python