/Python/Export keras model at specific epoch

Export keras model at specific epoch

import keras

class CustomSaver(keras.callbacks.Callback):
    def on_epoch_end(self, epoch, logs={}):
        if epoch == 2:  # or save after some epoch, each k-th epoch etc.
            self.model.save("model_{}.hd5".format(epoch))

Source: stackoverflow.com

Export keras model at specific epoch

import keras
import numpy as np

inp = keras.layers.Input(shape=(10,))
dense = keras.layers.Dense(10, activation='relu')(inp)
out = keras.layers.Dense(1, activation='sigmoid')(dense)
model = keras.models.Model(inp, out)
model.compile(optimizer="adam", loss="binary_crossentropy",)

# Just a noise data for fast working example
X = np.random.normal(0, 1, (1000, 10))
y = np.random.randint(0, 2, 1000)

# create and use callback:
saver = CustomSaver()
model.fit(X, y, callbacks=[saver], epochs=5)

-1

Source: stackoverflow.com

Similar codes

1 vote242 views1 answer
Flask socketio usage
Python Flask
-4 votes232 views5 answers
Python 3.6 release date
Python
4 votes189 views1 answer
Pandas concat reset index
Python
11 votes250 views3 answers
How to remove na values in r data frame
Python
0 vote237 views1 answer
Generate python
Python
0 vote226 views1 answer
Delete all historical data django simple history
Python Django
0 vote227 views2 answers
Write a pseudo code for generating a fibonacci series starting with 0 and 1 for 10 values using while loop.
Python
4 votes241 views2 answers
One hot encoding python pandas
Python
0 vote244 views1 answer
.replace pandas in for loop
Python
1 vote242 views2 answers
TypeError: list indices must be integers or slices, not str
Python