/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

8 votes196 views1 answer
Module to read keyboard
Python
0 vote218 views1 answer
Crank nicholson scheme python
Python
1 vote214 views1 answer
Lru cache python
Python
1 vote303 views2 answers
Divide a value by all values in a list
Python
3 votes222 views1 answer
Tkinter canvas remove
Python
0 vote199 views3 answers
Saving 3D plots on python as png
Python
91 votes242 views6 answers
Python for in
Python
0 vote264 views1 answer
The Bytearray Type
Python
1 vote195 views2 answers
Python sort list of integers
Python
0 vote212 views1 answer
Python how to geather and spread using pandas
Python