Python keras.optimizers.deserialize() Examples

The following are 13 code examples of keras.optimizers.deserialize(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module keras.optimizers , or try the search function .
Example #1
Source File: workers.py    From dist-keras with GNU General Public License v3.0 6 votes vote down vote up 
def prepare_model(self):
        """Prepares the model for training."""
        # Set the Keras directory.
        set_keras_base_directory()
        if K.backend() == 'tensorflow':
            # set GPU option allow_growth to False for GPU-enabled tensorflow
            config = tf.ConfigProto()
            config.gpu_options.allow_growth = False
            sess = tf.Session(config=config)
            K.set_session(sess)

        # Deserialize the Keras model.
        self.model = deserialize_keras_model(self.model)
        self.optimizer = deserialize(self.optimizer)
        # Compile the model with the specified loss and optimizer.
        self.model.compile(loss=self.loss, loss_weights = self.loss_weights, 
            optimizer=self.optimizer, metrics=self.metrics)
Example #2
Source File: optimizers.py    From keras-contrib with MIT License 5 votes vote down vote up 
def _test_optimizer(optimizer, target=0.75):
    x_train, y_train = get_test_data()
    model = get_model(x_train.shape[1], 10, y_train.shape[1])
    model.compile(loss='categorical_crossentropy',
                  optimizer=optimizer,
                  metrics=['accuracy'])
    history = model.fit(x_train, y_train, epochs=2, batch_size=16, verbose=0)
    assert history.history['acc'][-1] >= target
    config = optimizers.serialize(optimizer)
    custom_objects = {optimizer.__class__.__name__: optimizer.__class__}
    optim = optimizers.deserialize(config, custom_objects)
    new_config = optimizers.serialize(optim)
    assert config == new_config
Example #3
Source File: optimizers_test.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def _test_optimizer(optimizer, target=0.75):
    x_train, y_train = get_test_data()

    model = Sequential()
    model.add(Dense(10, input_shape=(x_train.shape[1],)))
    model.add(Activation('relu'))
    model.add(Dense(y_train.shape[1]))
    model.add(Activation('softmax'))
    model.compile(loss='categorical_crossentropy',
                  optimizer=optimizer,
                  metrics=['accuracy'])

    history = model.fit(x_train, y_train, epochs=2, batch_size=16, verbose=0)
    assert history.history['acc'][-1] >= target
    config = optimizers.serialize(optimizer)
    optim = optimizers.deserialize(config)
    new_config = optimizers.serialize(optim)
    new_config['class_name'] = new_config['class_name'].lower()
    assert config == new_config

    # Test constraints.
    model = Sequential()
    dense = Dense(10,
                  input_shape=(x_train.shape[1],),
                  kernel_constraint=lambda x: 0. * x + 1.,
                  bias_constraint=lambda x: 0. * x + 2.,)
    model.add(dense)
    model.add(Activation('relu'))
    model.add(Dense(y_train.shape[1]))
    model.add(Activation('softmax'))
    model.compile(loss='categorical_crossentropy',
                  optimizer=optimizer,
                  metrics=['accuracy'])
    model.train_on_batch(x_train[:10], y_train[:10])
    kernel, bias = dense.get_weights()
    assert_allclose(kernel, 1.)
    assert_allclose(bias, 2.)
Example #4
Source File: optimizers_test.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def _test_optimizer(optimizer, target=0.75):
    x_train, y_train = get_test_data()

    model = Sequential()
    model.add(Dense(10, input_shape=(x_train.shape[1],)))
    model.add(Activation('relu'))
    model.add(Dense(y_train.shape[1]))
    model.add(Activation('softmax'))
    model.compile(loss='categorical_crossentropy',
                  optimizer=optimizer,
                  metrics=['accuracy'])

    history = model.fit(x_train, y_train, epochs=2, batch_size=16, verbose=0)
    assert history.history['acc'][-1] >= target
    config = optimizers.serialize(optimizer)
    optim = optimizers.deserialize(config)
    new_config = optimizers.serialize(optim)
    new_config['class_name'] = new_config['class_name'].lower()
    assert config == new_config

    # Test constraints.
    model = Sequential()
    dense = Dense(10,
                  input_shape=(x_train.shape[1],),
                  kernel_constraint=lambda x: 0. * x + 1.,
                  bias_constraint=lambda x: 0. * x + 2.,)
    model.add(dense)
    model.add(Activation('relu'))
    model.add(Dense(y_train.shape[1]))
    model.add(Activation('softmax'))
    model.compile(loss='categorical_crossentropy',
                  optimizer=optimizer,
                  metrics=['accuracy'])
    model.train_on_batch(x_train[:10], y_train[:10])
    kernel, bias = dense.get_weights()
    assert_allclose(kernel, 1.)
    assert_allclose(bias, 2.)
Example #5
Source File: optimizers_test.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def _test_optimizer(optimizer, target=0.75):
    x_train, y_train = get_test_data()

    model = Sequential()
    model.add(Dense(10, input_shape=(x_train.shape[1],)))
    model.add(Activation('relu'))
    model.add(Dense(y_train.shape[1]))
    model.add(Activation('softmax'))
    model.compile(loss='categorical_crossentropy',
                  optimizer=optimizer,
                  metrics=['accuracy'])

    history = model.fit(x_train, y_train, epochs=2, batch_size=16, verbose=0)
    assert history.history['acc'][-1] >= target
    config = optimizers.serialize(optimizer)
    optim = optimizers.deserialize(config)
    new_config = optimizers.serialize(optim)
    new_config['class_name'] = new_config['class_name'].lower()
    assert config == new_config

    # Test constraints.
    model = Sequential()
    dense = Dense(10,
                  input_shape=(x_train.shape[1],),
                  kernel_constraint=lambda x: 0. * x + 1.,
                  bias_constraint=lambda x: 0. * x + 2.,)
    model.add(dense)
    model.add(Activation('relu'))
    model.add(Dense(y_train.shape[1]))
    model.add(Activation('softmax'))
    model.compile(loss='categorical_crossentropy',
                  optimizer=optimizer,
                  metrics=['accuracy'])
    model.train_on_batch(x_train[:10], y_train[:10])
    kernel, bias = dense.get_weights()
    assert_allclose(kernel, 1.)
    assert_allclose(bias, 2.)
Example #6
Source File: optimizers_test.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def _test_optimizer(optimizer, target=0.75):
    x_train, y_train = get_test_data()

    model = Sequential()
    model.add(Dense(10, input_shape=(x_train.shape[1],)))
    model.add(Activation('relu'))
    model.add(Dense(y_train.shape[1]))
    model.add(Activation('softmax'))
    model.compile(loss='categorical_crossentropy',
                  optimizer=optimizer,
                  metrics=['accuracy'])

    history = model.fit(x_train, y_train, epochs=2, batch_size=16, verbose=0)
    assert history.history['acc'][-1] >= target
    config = optimizers.serialize(optimizer)
    optim = optimizers.deserialize(config)
    new_config = optimizers.serialize(optim)
    new_config['class_name'] = new_config['class_name'].lower()
    assert config == new_config

    # Test constraints.
    model = Sequential()
    dense = Dense(10,
                  input_shape=(x_train.shape[1],),
                  kernel_constraint=lambda x: 0. * x + 1.,
                  bias_constraint=lambda x: 0. * x + 2.,)
    model.add(dense)
    model.add(Activation('relu'))
    model.add(Dense(y_train.shape[1]))
    model.add(Activation('softmax'))
    model.compile(loss='categorical_crossentropy',
                  optimizer=optimizer,
                  metrics=['accuracy'])
    model.train_on_batch(x_train[:10], y_train[:10])
    kernel, bias = dense.get_weights()
    assert_allclose(kernel, 1.)
    assert_allclose(bias, 2.)
Example #7
Source File: optimizers_test.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def _test_optimizer(optimizer, target=0.75):
    x_train, y_train = get_test_data()

    model = Sequential()
    model.add(Dense(10, input_shape=(x_train.shape[1],)))
    model.add(Activation('relu'))
    model.add(Dense(y_train.shape[1]))
    model.add(Activation('softmax'))
    model.compile(loss='categorical_crossentropy',
                  optimizer=optimizer,
                  metrics=['accuracy'])

    history = model.fit(x_train, y_train, epochs=2, batch_size=16, verbose=0)
    assert history.history['acc'][-1] >= target
    config = optimizers.serialize(optimizer)
    optim = optimizers.deserialize(config)
    new_config = optimizers.serialize(optim)
    new_config['class_name'] = new_config['class_name'].lower()
    assert config == new_config

    # Test constraints.
    model = Sequential()
    dense = Dense(10,
                  input_shape=(x_train.shape[1],),
                  kernel_constraint=lambda x: 0. * x + 1.,
                  bias_constraint=lambda x: 0. * x + 2.,)
    model.add(dense)
    model.add(Activation('relu'))
    model.add(Dense(y_train.shape[1]))
    model.add(Activation('softmax'))
    model.compile(loss='categorical_crossentropy',
                  optimizer=optimizer,
                  metrics=['accuracy'])
    model.train_on_batch(x_train[:10], y_train[:10])
    kernel, bias = dense.get_weights()
    assert_allclose(kernel, 1.)
    assert_allclose(bias, 2.)
Example #8
Source File: optimizers_test.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def _test_optimizer(optimizer, target=0.75):
    x_train, y_train = get_test_data()

    model = Sequential()
    model.add(Dense(10, input_shape=(x_train.shape[1],)))
    model.add(Activation('relu'))
    model.add(Dense(y_train.shape[1]))
    model.add(Activation('softmax'))
    model.compile(loss='categorical_crossentropy',
                  optimizer=optimizer,
                  metrics=['accuracy'])

    history = model.fit(x_train, y_train, epochs=2, batch_size=16, verbose=0)
    assert history.history['acc'][-1] >= target
    config = optimizers.serialize(optimizer)
    optim = optimizers.deserialize(config)
    new_config = optimizers.serialize(optim)
    new_config['class_name'] = new_config['class_name'].lower()
    assert config == new_config

    # Test constraints.
    model = Sequential()
    dense = Dense(10,
                  input_shape=(x_train.shape[1],),
                  kernel_constraint=lambda x: 0. * x + 1.,
                  bias_constraint=lambda x: 0. * x + 2.,)
    model.add(dense)
    model.add(Activation('relu'))
    model.add(Dense(y_train.shape[1]))
    model.add(Activation('softmax'))
    model.compile(loss='categorical_crossentropy',
                  optimizer=optimizer,
                  metrics=['accuracy'])
    model.train_on_batch(x_train[:10], y_train[:10])
    kernel, bias = dense.get_weights()
    assert_allclose(kernel, 1.)
    assert_allclose(bias, 2.)
Example #9
Source File: optimizers_test.py    From DeepLearning_Wavelet-LSTM with MIT License 5 votes vote down vote up 
def _test_optimizer(optimizer, target=0.75):
    x_train, y_train = get_test_data()

    model = Sequential()
    model.add(Dense(10, input_shape=(x_train.shape[1],)))
    model.add(Activation('relu'))
    model.add(Dense(y_train.shape[1]))
    model.add(Activation('softmax'))
    model.compile(loss='categorical_crossentropy',
                  optimizer=optimizer,
                  metrics=['accuracy'])

    history = model.fit(x_train, y_train, epochs=2, batch_size=16, verbose=0)
    assert history.history['acc'][-1] >= target
    config = optimizers.serialize(optimizer)
    optim = optimizers.deserialize(config)
    new_config = optimizers.serialize(optim)
    new_config['class_name'] = new_config['class_name'].lower()
    assert config == new_config

    # Test constraints.
    model = Sequential()
    dense = Dense(10,
                  input_shape=(x_train.shape[1],),
                  kernel_constraint=lambda x: 0. * x + 1.,
                  bias_constraint=lambda x: 0. * x + 2.,)
    model.add(dense)
    model.add(Activation('relu'))
    model.add(Dense(y_train.shape[1]))
    model.add(Activation('softmax'))
    model.compile(loss='categorical_crossentropy',
                  optimizer=optimizer,
                  metrics=['accuracy'])
    model.train_on_batch(x_train[:10], y_train[:10])
    kernel, bias = dense.get_weights()
    assert_allclose(kernel, 1.)
    assert_allclose(bias, 2.)
Example #10
Source File: optimizers_test.py    From faceswap with GNU General Public License v3.0 5 votes vote down vote up 
def _test_optimizer(optimizer, target=0.75):
    x_train, y_train = get_test_data()

    model = Sequential()
    model.add(Dense(10, input_shape=(x_train.shape[1],)))
    model.add(Activation('relu'))
    model.add(Dense(y_train.shape[1]))
    model.add(Activation('softmax'))
    model.compile(loss='categorical_crossentropy',
                  optimizer=optimizer,
                  metrics=['accuracy'])

    history = model.fit(x_train, y_train, epochs=2, batch_size=16, verbose=0)
    # TODO PlaidML fails this test
    assert history.history['acc'][-1] >= target
    config = k_optimizers.serialize(optimizer)
    optim = k_optimizers.deserialize(config)
    new_config = k_optimizers.serialize(optim)
    new_config['class_name'] = new_config['class_name'].lower()
    assert config == new_config

    # Test constraints.
    model = Sequential()
    dense = Dense(10,
                  input_shape=(x_train.shape[1],),
                  kernel_constraint=lambda x: 0. * x + 1.,
                  bias_constraint=lambda x: 0. * x + 2.,)
    model.add(dense)
    model.add(Activation('relu'))
    model.add(Dense(y_train.shape[1]))
    model.add(Activation('softmax'))
    model.compile(loss='categorical_crossentropy',
                  optimizer=optimizer,
                  metrics=['accuracy'])
    model.train_on_batch(x_train[:10], y_train[:10])
    kernel, bias = dense.get_weights()
    assert_allclose(kernel, 1.)
    assert_allclose(bias, 2.)
Example #11
Source File: util.py    From keras-rl with MIT License 5 votes vote down vote up 
def clone_optimizer(optimizer):
    if type(optimizer) is str:
        return optimizers.get(optimizer)
    # Requires Keras 1.0.7 since get_config has breaking changes.
    params = dict([(k, v) for k, v in optimizer.get_config().items()])
    config = {
        'class_name': optimizer.__class__.__name__,
        'config': params,
    }
    if hasattr(optimizers, 'optimizer_from_config'):
        # COMPATIBILITY: Keras < 2.0
        clone = optimizers.optimizer_from_config(config)
    else:
        clone = optimizers.deserialize(config)
    return clone
Example #12
Source File: optimizer.py    From mpi_learn with GNU General Public License v3.0 5 votes vote down vote up 
def build(self):
        from keras.optimizers import deserialize
        opt_config = {'class_name': self.name, 'config': self.config}
        opt = deserialize(opt_config)
        if self.horovod_wrapper:
            import horovod.keras as hvd
            if hasattr(opt, 'lr'):
                opt.lr *= hvd.size()
            opt = hvd.DistributedOptimizer(opt)
        return opt
Example #13
Source File: l2optimizer.py    From DIIN-in-Keras with MIT License 5 votes vote down vote up 
def from_config(cls, config, custom_objects=None):
        optimizer_config = config.pop('optimizer')
        optimizer = deserialize(optimizer_config)
        return cls(optimizer=optimizer, **config)