/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

2 votes218 views1 answer
Lower upper in pytho
Python
0 vote204 views1 answer
Dataframe summarize how many in each column
Python
10 votes190 views3 answers
String to hex python
Python
1 vote257 views1 answer
Posted data to flask
Python
2 votes214 views1 answer
Jsonresponse status code
Python
103 votes273 views4 answers
Separate a string in python
Python
0 vote258 views1 answer
What is iterator in python
Python
11 votes148 views5 answers
Encryption and decryption in python
Python
0 vote192 views1 answer
Select random img in python using os.listdir
Python
1 vote191 views1 answer
Python try/except loop
Python