/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

42 votes148 views6 answers
Python comment
Python
26 votes272 views6 answers
Flask run
Python Flask
3 votes142 views3 answers
Run flask in debug mode
Python
0 vote213 views1 answer
Unsupported media type django
Python Django
1 vote151 views1 answer
How to check for duplicates in a column in python
Python
3 votes98 views1 answer
Torch mse loss
Python
0 vote143 views1 answer
Python next item in list
Python
-2 votes143 views2 answers
Convert list of list to list python
Python
26 votes142 views3 answers
Check if variable is empty python
Python
3 votes125 views1 answer
Python numpy group by count
Python