Python keras.optimizers.RMSprop() Examples

def optimizer(self):
        a = K.placeholder(shape=(None,), dtype='int32')
        y = K.placeholder(shape=(None,), dtype='float32')

        py_x = self.model.output

        a_one_hot = K.one_hot(a, self.action_size)
        q_value = K.sum(py_x * a_one_hot, axis=1)
        error = K.abs(y - q_value)

        quadratic_part = K.clip(error, 0.0, 1.0)
        linear_part = error - quadratic_part
        loss = K.mean(0.5 * K.square(quadratic_part) + linear_part)

        optimizer = RMSprop(lr=0.00025, epsilon=0.01)
        updates = optimizer.get_updates(self.model.trainable_weights, [], loss)
        train = K.function([self.model.input, a, y], [loss], updates=updates)

        return train

    # approximate Q function using Convolution Neural Network
    # state is input and Q Value of each action is output of network 

def actor_optimizer(self):
        action = K.placeholder(shape=[None, self.action_size])
        advantages = K.placeholder(shape=[None, ])

        policy = self.actor.output

        good_prob = K.sum(action * policy, axis=1)
        eligibility = K.log(good_prob + 1e-10) * advantages
        actor_loss = -K.sum(eligibility)

        entropy = K.sum(policy * K.log(policy + 1e-10), axis=1)
        entropy = K.sum(entropy)

        loss = actor_loss + 0.01*entropy
        optimizer = RMSprop(lr=self.actor_lr, rho=0.99, epsilon=0.01)
        updates = optimizer.get_updates(self.actor.trainable_weights, [], loss)
        train = K.function([self.actor.input, action, advantages], [loss], updates=updates)

        return train

    # make loss function for Value approximation 

def optimizer(self):
        a = K.placeholder(shape=(None, ), dtype='int32')
        y = K.placeholder(shape=(None, ), dtype='float32')

        py_x = self.model.output

        a_one_hot = K.one_hot(a, self.action_size)
        q_value = K.sum(py_x * a_one_hot, axis=1)
        error = K.abs(y - q_value)

        quadratic_part = K.clip(error, 0.0, 1.0)
        linear_part = error - quadratic_part
        loss = K.mean(0.5 * K.square(quadratic_part) + linear_part)

        optimizer = RMSprop(lr=0.00025, epsilon=0.01)
        updates = optimizer.get_updates(self.model.trainable_weights, [], loss)
        train = K.function([self.model.input, a, y], [loss], updates=updates)

        return train

    # approximate Q function using Convolution Neural Network
    # state is input and Q Value of each action is output of network
    # dueling network's Q Value is sum of advantages and state value 

def SiameseNetwork(input_shape=(5880,)):
    base_network = create_base_network(input_shape)

    input_a = Input(shape=input_shape)
    input_b = Input(shape=input_shape)

    processed_a = base_network(input_a)
    processed_b = base_network(input_b)

    distance = Lambda(euclidean_distance,
                  output_shape=eucl_dist_output_shape)([processed_a, processed_b])

    model = Model([input_a, input_b], distance)

    rms = RMSprop()
    model.compile(loss=contrastive_loss, optimizer=rms, metrics=[accuracy])
    
    return model, base_network 

def buildmodel():
	print("Model building begins")

	model = Sequential()
	keras.initializers.RandomUniform(minval=-0.1, maxval=0.1, seed=None)

	S = Input(shape = (IMAGE_ROWS, IMAGE_COLS, IMAGE_CHANNELS, ), name = 'Input')
	h0 = Convolution2D(16, kernel_size = (8,8), strides = (4,4), activation = 'relu', kernel_initializer = 'random_uniform', bias_initializer = 'random_uniform')(S)
	h1 = Convolution2D(32, kernel_size = (4,4), strides = (2,2), activation = 'relu', kernel_initializer = 'random_uniform', bias_initializer = 'random_uniform')(h0)
	h2 = Flatten()(h1)
	h3 = Dense(256, activation = 'relu', kernel_initializer = 'random_uniform', bias_initializer = 'random_uniform') (h2)
	P = Dense(1, name = 'o_P', activation = 'sigmoid', kernel_initializer = 'random_uniform', bias_initializer = 'random_uniform') (h3)
	V = Dense(1, name = 'o_V', kernel_initializer = 'random_uniform', bias_initializer = 'random_uniform') (h3)

	model = Model(inputs = S, outputs = [P,V])
	rms = RMSprop(lr = LEARNING_RATE, rho = 0.99, epsilon = 0.1)
	model.compile(loss = {'o_P': logloss, 'o_V': sumofsquares}, loss_weights = {'o_P': 1., 'o_V' : 0.5}, optimizer = rms)
	return model

#function to preprocess an image before giving as input to the neural network 

def model_masking(discrete_time, init_alpha, max_beta):
    model = Sequential()

    model.add(Masking(mask_value=mask_value,
                      input_shape=(n_timesteps, n_features)))
    model.add(TimeDistributed(Dense(2)))
    model.add(Lambda(wtte.output_lambda, arguments={"init_alpha": init_alpha,
                                                    "max_beta_value": max_beta}))

    if discrete_time:
        loss = wtte.loss(kind='discrete', reduce_loss=False).loss_function
    else:
        loss = wtte.loss(kind='continuous', reduce_loss=False).loss_function

    model.compile(loss=loss, optimizer=RMSprop(
        lr=lr), sample_weight_mode='temporal')
    return model 

def test_train(self):
        train = pd.read_csv("/input/tests/data/train.csv")

        x_train = train.iloc[:,1:].values.astype('float32')
        y_train = to_categorical(train.iloc[:,0].astype('int32'))

        model = Sequential()
        model.add(Dense(units=10, input_dim=784, activation='softmax'))

        model.compile(
            loss='categorical_crossentropy',
            optimizer=RMSprop(lr=0.001),
            metrics=['accuracy'])

        model.fit(x_train, y_train, epochs=1, batch_size=32)

    # Uses convnet which depends on libcudnn when running on GPU 

def __init__(self, action_space, batch_size=32, screen=(84, 84), swap_freq=200):
        from keras.optimizers import RMSprop
        # -----
        self.screen = screen
        self.input_depth = 1
        self.past_range = 3
        self.observation_shape = (self.input_depth * self.past_range,) + self.screen
        self.batch_size = batch_size

        self.action_value = build_network(self.observation_shape, action_space.n)
        self.action_value.compile(optimizer=RMSprop(clipnorm=1.), loss='mse')

        self.losses = deque(maxlen=25)
        self.q_values = deque(maxlen=25)
        self.swap_freq = swap_freq
        self.swap_counter = self.swap_freq
        self.unroll = np.arange(self.batch_size)
        self.frames = 0 

def __init__(self, action_space, screen=(84, 84), n_step=8, discount=0.99):
        from keras.optimizers import RMSprop
        # -----
        self.screen = screen
        self.input_depth = 1
        self.past_range = 3
        self.observation_shape = (self.input_depth * self.past_range,) + self.screen

        self.action_value = build_network(self.observation_shape, action_space.n)
        self.action_value.compile(optimizer=RMSprop(clipnorm=1.), loss='mse')  # clipnorm=1.

        self.action_space = action_space
        self.observations = np.zeros(self.observation_shape)
        self.last_observations = np.zeros_like(self.observations)
        # -----
        self.n_step_observations = deque(maxlen=n_step)
        self.n_step_actions = deque(maxlen=n_step)
        self.n_step_rewards = deque(maxlen=n_step)
        self.n_step = n_step
        self.discount = discount
        self.counter = 0 

def __init__(self, action_space, batch_size=32, screen=(84, 84), swap_freq=200):
        from keras.optimizers import RMSprop		
        # -----
        self.screen = screen
        self.input_depth = 1
        self.past_range = 3
        self.observation_shape = (self.input_depth * self.past_range,) + self.screen
        self.batch_size = batch_size

        _, _, self.train_net, adventage = build_network(self.observation_shape, action_space.n)

        self.train_net.compile(optimizer=RMSprop(epsilon=0.1, rho=0.99),
                               loss=[value_loss(), policy_loss(adventage, args.beta)])

        self.pol_loss = deque(maxlen=25)
        self.val_loss = deque(maxlen=25)
        self.values = deque(maxlen=25)
        self.entropy = deque(maxlen=25)
        self.swap_freq = swap_freq
        self.swap_counter = self.swap_freq
        self.unroll = np.arange(self.batch_size)
        self.targets = np.zeros((self.batch_size, action_space.n))
        self.counter = 0 

def get_optimizer(args):

	clipvalue = 0
	clipnorm = 10

	if args.algorithm == 'rmsprop':
		optimizer = opt.RMSprop(lr=0.001, rho=0.9, epsilon=1e-06, clipnorm=clipnorm, clipvalue=clipvalue)
	elif args.algorithm == 'sgd':
		optimizer = opt.SGD(lr=0.01, momentum=0.0, decay=0.0, nesterov=False, clipnorm=clipnorm, clipvalue=clipvalue)
	elif args.algorithm == 'adagrad':
		optimizer = opt.Adagrad(lr=0.01, epsilon=1e-06, clipnorm=clipnorm, clipvalue=clipvalue)
	elif args.algorithm == 'adadelta':
		optimizer = opt.Adadelta(lr=1.0, rho=0.95, epsilon=1e-06, clipnorm=clipnorm, clipvalue=clipvalue)
	elif args.algorithm == 'adam':
		optimizer = opt.Adam(lr=0.001, beta_1=0.9, beta_2=0.999, epsilon=1e-08, clipnorm=clipnorm, clipvalue=clipvalue)
	elif args.algorithm == 'adamax':
		optimizer = opt.Adamax(lr=0.002, beta_1=0.9, beta_2=0.999, epsilon=1e-08, clipnorm=clipnorm, clipvalue=clipvalue)
	
	return optimizer 

def get_optimizer(config):
    if config.OPTIMIZER == 'SGD':
        return SGD(lr=config.LEARNING_RATE, momentum=config.LEARNING_MOMENTUM, clipnorm=config.GRADIENT_CLIP_NORM, nesterov=config.NESTEROV)
    elif config.OPTIMIZER == 'RMSprop':
        return RMSprop(lr=config.LEARNING_RATE, clipnorm=config.GRADIENT_CLIP_NORM)
    elif config.OPTIMIZER == 'Adagrad':
        return Adagrad(lr=config.LEARNING_RATE, clipnorm=config.GRADIENT_CLIP_NORM)
    elif config.OPTIMIZER == 'Adadelta':
        return Adadelta(lr=config.LEARNING_RATE, clipnorm=config.GRADIENT_CLIP_NORM)
    elif config.OPTIMIZER == 'Adam':
        return Adam(lr=config.LEARNING_RATE, clipnorm=config.GRADIENT_CLIP_NORM, amsgrad=config.AMSGRAD)
    elif config.OPTIMIZER == 'Adamax':
        return Adamax(lr=config.LEARNING_RATE, clipnorm=config.GRADIENT_CLIP_NORM)
    elif config.OPTIMIZER == 'Nadam':
        return Nadam(lr=config.LEARNING_RATE, clipnorm=config.GRADIENT_CLIP_NORM)
    else:
        raise Exception('Unrecognized optimizer: {}'.format(config.OPTIMIZER)) 

def fit_new(self, x, y=None):
        timesteps = x.shape[1]
        input_dim = x.shape[2]
        self.ae = Sequential()
        self.ae.add(Dense(self.latent_dim,
                    input_shape=(timesteps,input_dim,),
                    activation='relu',
                    name='enc'))
        self.ae.add(Dropout(0.2))
        self.ae.add(Dense(input_dim,
                    activation='softmax',
                    name='dec'))

        self.encoder = Model(inputs=self.ae.input,
                             outputs=self.ae.get_layer('enc').output)
        #rmsprop = RMSprop(lr=0.05)
        self.ae.compile(loss='categorical_crossentropy',
                  optimizer='adam',
                  metrics=['categorical_accuracy'],)
        self.ae.fit(x, x, epochs=1) 

def fit_dep(self, x, y=None):
        timesteps = x.shape[1]
        input_dim = x.shape[2]
        inputs = Input(shape=(timesteps, input_dim))
        encoded = LSTM(self.latent_dim)(inputs)

        decoded = RepeatVector(timesteps)(encoded)
        decoded = LSTM(input_dim, return_sequences=True)(decoded)

        encoded_input = Input(shape=(self.latent_dim,))

        self.sequence_autoencoder = Model(inputs, decoded)
        self.encoder = Model(inputs, encoded)

        self.sequence_autoencoder.compile(
            #loss='binary_crossentropy',
            loss='categorical_crossentropy',
            optimizer='RMSprop',
            metrics=['binary_accuracy']
        )
        self.sequence_autoencoder.fit(x, x) 

def create_model(layer_sizes1, layer_sizes2, input_size1, input_size2,
                    learning_rate, reg_par, outdim_size, use_all_singular_values):
    """
    builds the whole model
    the structure of each sub-network is defined in build_mlp_net,
    and it can easily get substituted with a more efficient and powerful network like CNN
    """
    view1_model = build_mlp_net(layer_sizes1, input_size1, reg_par)
    view2_model = build_mlp_net(layer_sizes2, input_size2, reg_par)

    model = Sequential()
    model.add(Merge([view1_model, view2_model], mode='concat'))

    model_optimizer = RMSprop(lr=learning_rate)
    model.compile(loss=cca_loss(outdim_size, use_all_singular_values), optimizer=model_optimizer)

    return model 

def init_model():
    """
    """
    start_time = time.time()
    print 'Compiling model...'
    model = Sequential()

    model.add(Convolution2D(64, 3,3, border_mode='valid', input_shape=INPUT_SHAPE))
    model.add(Activation('relu'))
    model.add(MaxPooling2D(pool_size=(2,2)))
    model.add(Dropout(.25))

    model.add(Flatten())

    model.add(Dense(10))
    model.add(Activation('softmax'))

    rms = RMSprop()
    model.compile(loss='categorical_crossentropy', optimizer=rms,
      metrics=['accuracy'])
    print 'Model compiled in {0} seconds'.format(time.time() - start_time)

    model.summary()
    return model 

def init_model():
    start_time = time.time()
    print 'Compiling Model ... '
    model = Sequential()
    model.add(Dense(500, input_dim=784))
    model.add(Activation('relu'))
    model.add(Dropout(0.4))
    model.add(Dense(300))
    model.add(Activation('relu'))
    model.add(Dropout(0.4))
    model.add(Dense(10))
    model.add(Activation('softmax'))

    rms = RMSprop()
    model.compile(loss='categorical_crossentropy', optimizer=rms,
      metrics=['accuracy'])
    print 'Model compiled in {0} seconds'.format(time.time() - start_time)
    return model 

def test_saving_lambda_custom_objects():
    inputs = Input(shape=(3,))
    x = Lambda(lambda x: square_fn(x), output_shape=(3,))(inputs)
    outputs = Dense(3)(x)

    model = Model(inputs, outputs)
    model.compile(loss=losses.MSE,
                  optimizer=optimizers.RMSprop(lr=0.0001),
                  metrics=[metrics.categorical_accuracy])
    x = np.random.random((1, 3))
    y = np.random.random((1, 3))
    model.train_on_batch(x, y)

    out = model.predict(x)
    _, fname = tempfile.mkstemp('.h5')
    save_model(model, fname)

    model = load_model(fname, custom_objects={'square_fn': square_fn})
    os.remove(fname)

    out2 = model.predict(x)
    assert_allclose(out, out2, atol=1e-05) 

def test_saving_custom_activation_function():
    x = Input(shape=(3,))
    output = Dense(3, activation=K.cos)(x)

    model = Model(x, output)
    model.compile(loss=losses.MSE,
                  optimizer=optimizers.RMSprop(lr=0.0001),
                  metrics=[metrics.categorical_accuracy])
    x = np.random.random((1, 3))
    y = np.random.random((1, 3))
    model.train_on_batch(x, y)

    out = model.predict(x)
    _, fname = tempfile.mkstemp('.h5')
    save_model(model, fname)

    model = load_model(fname, custom_objects={'cos': K.cos})
    os.remove(fname)

    out2 = model.predict(x)
    assert_allclose(out, out2, atol=1e-05) 

def test_saving_lambda_custom_objects():
    inputs = Input(shape=(3,))
    x = Lambda(lambda x: square_fn(x), output_shape=(3,))(inputs)
    outputs = Dense(3)(x)

    model = Model(inputs, outputs)
    model.compile(loss=losses.MSE,
                  optimizer=optimizers.RMSprop(lr=0.0001),
                  metrics=[metrics.categorical_accuracy])
    x = np.random.random((1, 3))
    y = np.random.random((1, 3))
    model.train_on_batch(x, y)

    out = model.predict(x)
    _, fname = tempfile.mkstemp('.h5')
    save_model(model, fname)

    model = load_model(fname, custom_objects={'square_fn': square_fn})
    os.remove(fname)

    out2 = model.predict(x)
    assert_allclose(out, out2, atol=1e-05) 

def test_saving_custom_activation_function():
    x = Input(shape=(3,))
    output = Dense(3, activation=K.cos)(x)

    model = Model(x, output)
    model.compile(loss=losses.MSE,
                  optimizer=optimizers.RMSprop(lr=0.0001),
                  metrics=[metrics.categorical_accuracy])
    x = np.random.random((1, 3))
    y = np.random.random((1, 3))
    model.train_on_batch(x, y)

    out = model.predict(x)
    _, fname = tempfile.mkstemp('.h5')
    save_model(model, fname)

    model = load_model(fname, custom_objects={'cos': K.cos})
    os.remove(fname)

    out2 = model.predict(x)
    assert_allclose(out, out2, atol=1e-05) 

def test_saving_lambda_custom_objects():
    inputs = Input(shape=(3,))
    x = Lambda(lambda x: square_fn(x), output_shape=(3,))(inputs)
    outputs = Dense(3)(x)

    model = Model(inputs, outputs)
    model.compile(loss=losses.MSE,
                  optimizer=optimizers.RMSprop(lr=0.0001),
                  metrics=[metrics.categorical_accuracy])
    x = np.random.random((1, 3))
    y = np.random.random((1, 3))
    model.train_on_batch(x, y)

    out = model.predict(x)
    _, fname = tempfile.mkstemp('.h5')
    save_model(model, fname)

    model = load_model(fname, custom_objects={'square_fn': square_fn})
    os.remove(fname)

    out2 = model.predict(x)
    assert_allclose(out, out2, atol=1e-05) 

def test_saving_lambda_custom_objects():
    inputs = Input(shape=(3,))
    x = Lambda(lambda x: square_fn(x), output_shape=(3,))(inputs)
    outputs = Dense(3)(x)

    model = Model(inputs, outputs)
    model.compile(loss=losses.MSE,
                  optimizer=optimizers.RMSprop(lr=0.0001),
                  metrics=[metrics.categorical_accuracy])
    x = np.random.random((1, 3))
    y = np.random.random((1, 3))
    model.train_on_batch(x, y)

    out = model.predict(x)
    _, fname = tempfile.mkstemp('.h5')
    save_model(model, fname)

    model = load_model(fname, custom_objects={'square_fn': square_fn})
    os.remove(fname)

    out2 = model.predict(x)
    assert_allclose(out, out2, atol=1e-05) 

def test_saving_custom_activation_function():
    x = Input(shape=(3,))
    output = Dense(3, activation=K.cos)(x)

    model = Model(x, output)
    model.compile(loss=losses.MSE,
                  optimizer=optimizers.RMSprop(lr=0.0001),
                  metrics=[metrics.categorical_accuracy])
    x = np.random.random((1, 3))
    y = np.random.random((1, 3))
    model.train_on_batch(x, y)

    out = model.predict(x)
    _, fname = tempfile.mkstemp('.h5')
    save_model(model, fname)

    model = load_model(fname, custom_objects={'cos': K.cos})
    os.remove(fname)

    out2 = model.predict(x)
    assert_allclose(out, out2, atol=1e-05) 

def test_saving_lambda_custom_objects():
    inputs = Input(shape=(3,))
    x = Lambda(lambda x: square_fn(x), output_shape=(3,))(inputs)
    outputs = Dense(3)(x)

    model = Model(inputs, outputs)
    model.compile(loss=losses.MSE,
                  optimizer=optimizers.RMSprop(lr=0.0001),
                  metrics=[metrics.categorical_accuracy])
    x = np.random.random((1, 3))
    y = np.random.random((1, 3))
    model.train_on_batch(x, y)

    out = model.predict(x)
    _, fname = tempfile.mkstemp('.h5')
    save_model(model, fname)

    model = load_model(fname, custom_objects={'square_fn': square_fn})
    os.remove(fname)

    out2 = model.predict(x)
    assert_allclose(out, out2, atol=1e-05) 

def test_saving_custom_activation_function():
    x = Input(shape=(3,))
    output = Dense(3, activation=K.cos)(x)

    model = Model(x, output)
    model.compile(loss=losses.MSE,
                  optimizer=optimizers.RMSprop(lr=0.0001),
                  metrics=[metrics.categorical_accuracy])
    x = np.random.random((1, 3))
    y = np.random.random((1, 3))
    model.train_on_batch(x, y)

    out = model.predict(x)
    _, fname = tempfile.mkstemp('.h5')
    save_model(model, fname)

    model = load_model(fname, custom_objects={'cos': K.cos})
    os.remove(fname)

    out2 = model.predict(x)
    assert_allclose(out, out2, atol=1e-05) 

def test_saving_lambda_custom_objects():
    inputs = Input(shape=(3,))
    x = Lambda(lambda x: square_fn(x), output_shape=(3,))(inputs)
    outputs = Dense(3)(x)

    model = Model(inputs, outputs)
    model.compile(loss=losses.MSE,
                  optimizer=optimizers.RMSprop(lr=0.0001),
                  metrics=[metrics.categorical_accuracy])
    x = np.random.random((1, 3))
    y = np.random.random((1, 3))
    model.train_on_batch(x, y)

    out = model.predict(x)
    _, fname = tempfile.mkstemp('.h5')
    save_model(model, fname)

    model = load_model(fname, custom_objects={'square_fn': square_fn})
    os.remove(fname)

    out2 = model.predict(x)
    assert_allclose(out, out2, atol=1e-05) 

def test_saving_lambda_custom_objects():
    inputs = Input(shape=(3,))
    x = Lambda(lambda x: square_fn(x), output_shape=(3,))(inputs)
    outputs = Dense(3)(x)

    model = Model(inputs, outputs)
    model.compile(loss=losses.MSE,
                  optimizer=optimizers.RMSprop(lr=0.0001),
                  metrics=[metrics.categorical_accuracy])
    x = np.random.random((1, 3))
    y = np.random.random((1, 3))
    model.train_on_batch(x, y)

    out = model.predict(x)
    _, fname = tempfile.mkstemp('.h5')
    save_model(model, fname)

    model = load_model(fname, custom_objects={'square_fn': square_fn})
    os.remove(fname)

    out2 = model.predict(x)
    assert_allclose(out, out2, atol=1e-05) 

def test_saving_custom_activation_function():
    x = Input(shape=(3,))
    output = Dense(3, activation=K.cos)(x)

    model = Model(x, output)
    model.compile(loss=losses.MSE,
                  optimizer=optimizers.RMSprop(lr=0.0001),
                  metrics=[metrics.categorical_accuracy])
    x = np.random.random((1, 3))
    y = np.random.random((1, 3))
    model.train_on_batch(x, y)

    out = model.predict(x)
    _, fname = tempfile.mkstemp('.h5')
    save_model(model, fname)

    model = load_model(fname, custom_objects={'cos': K.cos})
    os.remove(fname)

    out2 = model.predict(x)
    assert_allclose(out, out2, atol=1e-05) 

def test_saving_lambda_custom_objects():
    inputs = Input(shape=(3,))
    x = Lambda(lambda x: square_fn(x), output_shape=(3,))(inputs)
    outputs = Dense(3)(x)

    model = Model(inputs, outputs)
    model.compile(loss=losses.MSE,
                  optimizer=optimizers.RMSprop(lr=0.0001),
                  metrics=[metrics.categorical_accuracy])
    x = np.random.random((1, 3))
    y = np.random.random((1, 3))
    model.train_on_batch(x, y)

    out = model.predict(x)
    _, fname = tempfile.mkstemp('.h5')
    save_model(model, fname)

    model = load_model(fname, custom_objects={'square_fn': square_fn})
    os.remove(fname)

    out2 = model.predict(x)
    assert_allclose(out, out2, atol=1e-05)