/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 vote154 views1 answer
Random pick any file from directory python
Python
13 votes152 views3 answers
Python http server command line
Python
2 votes150 views2 answers
Tkinter treeview
Python
1 vote144 views1 answer
How to only print final iteration of a for loop pyhton
Python
0 vote143 views1 answer
Check if all elements in array are true python
Python
6 votes149 views3 answers
Tkinter filedialog filename
Python
0 vote162 views1 answer
Python tabulate without index
Python
1 vote143 views1 answer
How to use arjun tool
Python
0 vote154 views1 answer
Tb to pb with python calculator
Python
0 vote156 views1 answer
RemoveStopWords
Python