/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 vote175 views1 answer
Create button in pyqt
Python
0 vote191 views1 answer
"'S3' object has no attribute 'Bucket'", python boto3 aws
Python
1 vote182 views1 answer
Django genericforeignkey null
Python
0 vote253 views1 answer
Request.body django
Python Django
0 vote208 views1 answer
Autopytoexe
Python
0 vote194 views1 answer
Encrypt password with sha512 + python
Python
0 vote224 views1 answer
Python replace negative infinity
Python
39 votes197 views4 answers
How to make a comment in python
Python
0 vote206 views1 answer
ModuleNotFoundError: No module named 'rest_auth'
Python
8 votes201 views1 answer
Delete certain characters from a string python
Python