/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 vote271 views1 answer
Sheebang python
Python
1 vote281 views1 answer
Change index function for class python
Python
0 vote274 views1 answer
Python turtle set direction
Python
0 vote313 views1 answer
Comtypes python
Python
-1 vote292 views1 answer
Python type checking boolean
Python
0 vote286 views2 answers
Python argsort
Python
0 vote266 views1 answer
Regular Expression to Stop at First Match
Python
6 votes271 views4 answers
How to encrypt text in python
Python
1 vote369 views1 answer
Python get list of all open windows
Python
0 vote316 views1 answer
Dataframe plot conditional formatting
Python