/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

1 vote391 views3 answers
Link in embed discord.py
Python
0 vote369 views1 answer
Python how to run code in ssh
Python
1 vote383 views1 answer
Numpy series reset index
Python
-2 votes362 views2 answers
Python pyaudio error
Python
0 vote364 views1 answer
Hide verbose in pip install
Python
0 vote330 views1 answer
Python schedule task every hour
Python
0 vote325 views1 answer
How to restart a loop
Python
0 vote337 views1 answer
Python lvl up
Python
2 votes378 views2 answers
Python version installed in ubuntu
Python
0 vote330 views1 answer
Numpy distance of consecutive elements
Python