/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 vote191 views1 answer
Tkinter canas can you use other fonts
Python
0 vote176 views1 answer
Selenium how to handle element not found python
Python
1 vote243 views1 answer
Python access modifiers
Python
0 vote183 views1 answer
Find All Occurrences of start indices of the substrings in a String in Python
Python
2 votes188 views1 answer
How to change pygame window icon
Python
0 vote181 views1 answer
Numpy rolling 2d
Python
0 vote178 views1 answer
String without space pythonm
Python
0 vote184 views1 answer
Majority in array python
Python
0 vote189 views1 answer
How to add twoo segmen time series in a single plot
Python
0 vote198 views1 answer
How to find the summation of all the values in a tuple python
Python