/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

3 votes172 views3 answers
Run a shell script from python
Python
0 vote165 views2 answers
How to map longitude and latitude in python
Python
2 votes155 views1 answer
Copy website
Python
2 votes179 views2 answers
Pandas remove rows based on DATETIME column year
Python
0 vote155 views1 answer
Open gui window python
Python
2 votes153 views1 answer
Create pandas dataframe with random numbers
Python
0 vote189 views1 answer
How to change order of attributes of an element using beautiful soup
Python
0 vote169 views1 answer
Compute mean over y for same x numpy
Python
184 votes264 views6 answers
How to upgrade pip
Python
2 votes174 views1 answer
AlphaTauri
Python