web-dev-qa-db-fra.com

Comment figer des poids dans certaines couches avec Keras?

J'essaie de figer les poids de certaines couches dans un modèle de prédiction avec Keras et un ensemble de données mnist, mais cela ne fonctionne pas. Le code est comme:

from keras.layers import Dense, Flatten
from keras.utils import to_categorical
from keras.models import Sequential, load_model
from keras.datasets import mnist
from keras.losses import categorical_crossentropy

import numpy as np

def load_data():
    (x_train, y_train), (x_test, y_test) = mnist.load_data()
    x_train = x_train.astype('float32')
    x_test = x_test.astype('float32')
    x_train /= 255
    x_test /= 255
    y_train = to_categorical(y_train, num_classes=10)
    y_test = to_categorical(y_test, num_classes=10)
    return x_train, y_train, x_test, y_test


def run():
    x_train, y_train, x_test, y_test = load_data()
    model = Sequential([Flatten(input_shape=(28, 28)),
                        Dense(300, name='dense1', activation='relu'),
                        Dense(100, name='dense2', activation='relu'),
                        Dense(10, name='dense3', activation='softmax')])
    model.trainable = True
    model.compile(optimizer='Adam',
                  metrics=['accuracy'],
                  loss=categorical_crossentropy)

    print(model.summary())
    model.fit(x_train, y_train, epochs=5, verbose=2)
    print(model.evaluate(x_test, y_test))
    return model

def freeze(model):
    x_train, y_train, x_test, y_test = load_data()

    name = 'dense1'

    weightsAndBias = model.get_layer(name=name).get_weights()

    # freeze the weights of this layer
    model.get_layer(name=name).trainable = False

    # record the weights before retrain
    weights_before = weightsAndBias[0]
    # retrain
    model.fit(x_train, y_train, verbose=2, epochs=1)
    weights_after = model.get_layer(name=name).get_weights()[0]

    if (weights_before == weights_after).all():
        print('the weights did not change!!!')
    else:
        print('the weights changed!!!!')

if __name__ == '__main__':
    model = run()
    freeze(model)

Le programme affiche "les poids ont changé !!!!". Je ne comprends pas pourquoi les poids de la couche nommée 'dense1' changent après avoir défini model.get_layer(name=name).trainable = False.

tensorflowmachine-learningkerasmnist
3
david

Vous pouvez le faire en utilisant:

model=Sequential()
layer=Dense(64,init='glorot_uniform',input_shape=(784,))
layer.trainable=False
model.add(layer)
layer2=Dense(784, activation='sigmoid',init='glorot_uniform')
layer2.trainable=True
model.add(layer2)
model.compile(loss='relu', optimizer=sgd,metrics = ['mae'])
3
Rubens_Zimbres

Vous devez compiler le graphique après avoir défini "formable". https://keras.io/getting-started/faq/#how-can-i-freeze-keras-layers

2
Pedro Marques