Notes sur la programmation: Enregistrer et charger les paramètres en même temps

Contenu du didacticiel

Preparation
1. Vagrant et Virtual Box.

2. Apache

3. MySQL

4. Python

5. Python Hello World

Apprentissage profond
1. Installer Keras et tester l'apprentissage profond (Deep learning)

2. Enregistrer et charger les paramètres

3. Enregistrer et charger les paramètres en même temps

4. Utiliser son propre le jeu de données

Enregistrer et charger les paramètres en même temps

1. Créer un fichier "reuters_tosaveload.py" et ouvrir le fichier. Écrire dedans:

#!/usr/bin/env python
# -*- coding: UTF-8 -*-

'''Trains and evaluate a simple MLP
on the Reuters newswire topic classification task.
'''
from __future__ import print_function

import numpy as np
import keras
from keras.datasets import reuters
from keras.models import Sequential
from keras.models import model_from_json
from keras.layers import Dense, Dropout, Activation
from keras.utils import np_utils
from keras.optimizers import Adam
from keras.preprocessing.text import Tokenizer
import keras.callbacks
import keras.backend.tensorflow_backend as KTF
import tensorflow as tf
import os.path

f_log = './'
f_model = './'
model_filename = 'reuters_model.json'
weights_filename = 'reuters_model_weights.hdf5'

max_words = 1000
batch_size = 32
epochs = 5

print('Loading data...')
(x_train, y_train), (x_test, y_test) = reuters.load_data(num_words=max_words,
test_split=0.2)
print(len(x_train), 'train sequences')
print(len(x_test), 'test sequences')

num_classes = np.max(y_train) + 1
print(num_classes, 'classes')

print('Vectorizing sequence data...')
tokenizer = Tokenizer(num_words=max_words)
x_train = tokenizer.sequences_to_matrix(x_train, mode='binary')
x_test = tokenizer.sequences_to_matrix(x_test, mode='binary')
print('x_train shape:', x_train.shape)
print('x_test shape:', x_test.shape)

print('Convert class vector to binary class matrix '
'(for use with categorical_crossentropy)')
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)

old_session = KTF.get_session()

print('y_train shape:', y_train.shape)
print('y_test shape:', y_test.shape)

print('Building model...')
session = tf.Session('')
KTF.set_session(session)

json_string = open(os.path.join(f_model, model_filename)).read()
model = model_from_json(json_string)

model.summary()
model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])
model.load_weights(os.path.join(f_model,weights_filename))

tb_cb = keras.callbacks.TensorBoard(log_dir=f_log, histogram_freq=0)
cp_cb = keras.callbacks.ModelCheckpoint(filepath = os.path.join(f_model,'reuters_model{epoch:02d}-loss{loss:.2f}-acc{acc:.2f}-vloss{val_loss:.2f}-vacc{val_acc:.2f}.hdf5'), monitor='val_loss', verbose=1, save_best_only=True, mode='auto')
cbks = [tb_cb, cp_cb]

history = model.fit(x_train, y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_split=0.1,
callbacks=cbks)
score = model.evaluate(x_test, y_test,
batch_size=batch_size, verbose=1)
print('')
print('Test score:', score[0])
print('Test accuracy:', score[1])
print('save the architecture of a model')

json_string = model.to_json()
open(os.path.join(f_model,'reuters_model.json'), 'w').write(json_string)
yaml_string = model.to_yaml()
open(os.path.join(f_model,'reuters_model.yaml'), 'w').write(yaml_string)
print('save weights')
model.save_weights(os.path.join(f_model,'reuters_model_weights.hdf5'))
KTF.set_session(old_session)

Ce fichier va enregistrer et charger les paramètres en même temps. Mais nous devons créer le fichier de "reuters_model.json" par faire ce code avant faire ce fichier. Si vous le finissez et créer le fichier, faire ces commandes:

$ sudo cd /vagrant
$ python3 reuters_tosaveload.php

Et l'apprentissage va démarrer: