/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 vote94 views1 answer
Binary string to hex python
Python
0 vote102 views1 answer
Using default as none in django mdoels
Python
0 vote107 views1 answer
Django many to many post update method via rest
Python
0 vote114 views1 answer
Djangobook.com jwd django restfremwork plugin
Python
9 votes102 views8 answers
Python loop
Python
1 vote147 views1 answer
Django genericforeignkey null
Python Django
1 vote101 views2 answers
Numpy one hot
Python
68 votes111 views6 answers
Create a directory python
Python
0 vote103 views1 answer
Label_map dict = label_map_util.get_label_map_dict(label_map)
Python
6 votes97 views1 answer
Change dataframe value by index
Python