Python lasagne.updates.adagrad() Examples
The following are 7
code examples of lasagne.updates.adagrad().
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
lasagne.updates
, or try the search function
.
.
Example #1
| Source File: nn_adagrad_pca.py From kaggle_otto with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def create_iter_functions(self, dataset, output_layer, X_tensor_type=T.matrix):
batch_index = T.iscalar('batch_index')
X_batch = X_tensor_type('x')
y_batch = T.ivector('y')
batch_slice = slice(batch_index * self.batch_size, (batch_index + 1) * self.batch_size)
objective = Objective(output_layer, loss_function=categorical_crossentropy)
loss_train = objective.get_loss(X_batch, target=y_batch)
loss_eval = objective.get_loss(X_batch, target=y_batch, deterministic=True)
pred = T.argmax(output_layer.get_output(X_batch, deterministic=True), axis=1)
proba = output_layer.get_output(X_batch, deterministic=True)
accuracy = T.mean(T.eq(pred, y_batch), dtype=theano.config.floatX)
all_params = get_all_params(output_layer)
updates = adagrad(loss_train, all_params, self.lr, self.epsilon)
iter_train = theano.function(
[batch_index], loss_train,
updates=updates,
givens={
X_batch: dataset['X_train'][batch_slice],
y_batch: dataset['y_train'][batch_slice],
},
on_unused_input='ignore',
)
iter_valid = None
if self.use_valid:
iter_valid = theano.function(
[batch_index], [loss_eval, accuracy, proba],
givens={
X_batch: dataset['X_valid'][batch_slice],
y_batch: dataset['y_valid'][batch_slice],
},
)
return dict(train=iter_train, valid=iter_valid)
Example #2
| Source File: nn_adagrad_log.py From kaggle_otto with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def create_iter_functions(self, dataset, output_layer, X_tensor_type=T.matrix):
batch_index = T.iscalar('batch_index')
X_batch = X_tensor_type('x')
y_batch = T.ivector('y')
batch_slice = slice(batch_index * self.batch_size, (batch_index + 1) * self.batch_size)
objective = Objective(output_layer, loss_function=categorical_crossentropy)
loss_train = objective.get_loss(X_batch, target=y_batch)
loss_eval = objective.get_loss(X_batch, target=y_batch, deterministic=True)
pred = T.argmax(output_layer.get_output(X_batch, deterministic=True), axis=1)
proba = output_layer.get_output(X_batch, deterministic=True)
accuracy = T.mean(T.eq(pred, y_batch), dtype=theano.config.floatX)
all_params = get_all_params(output_layer)
updates = adagrad(loss_train, all_params, self.lr, self.rho)
iter_train = theano.function(
[batch_index], loss_train,
updates=updates,
givens={
X_batch: dataset['X_train'][batch_slice],
y_batch: dataset['y_train'][batch_slice],
},
on_unused_input='ignore',
)
iter_valid = None
if self.use_valid:
iter_valid = theano.function(
[batch_index], [loss_eval, accuracy, proba],
givens={
X_batch: dataset['X_valid'][batch_slice],
y_batch: dataset['y_valid'][batch_slice],
},
)
return dict(train=iter_train, valid=iter_valid)
Example #3
| Source File: nn_adagrad_pca.py From kaggle_otto with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def create_iter_functions(self, dataset, output_layer, X_tensor_type=T.matrix):
batch_index = T.iscalar('batch_index')
X_batch = X_tensor_type('x')
y_batch = T.ivector('y')
batch_slice = slice(batch_index * self.batch_size, (batch_index + 1) * self.batch_size)
objective = Objective(output_layer, loss_function=categorical_crossentropy)
loss_train = objective.get_loss(X_batch, target=y_batch)
loss_eval = objective.get_loss(X_batch, target=y_batch, deterministic=True)
pred = T.argmax(output_layer.get_output(X_batch, deterministic=True), axis=1)
proba = output_layer.get_output(X_batch, deterministic=True)
accuracy = T.mean(T.eq(pred, y_batch), dtype=theano.config.floatX)
all_params = get_all_params(output_layer)
updates = adagrad(loss_train, all_params, self.lr, self.epsilon)
iter_train = theano.function(
[batch_index], loss_train,
updates=updates,
givens={
X_batch: dataset['X_train'][batch_slice],
y_batch: dataset['y_train'][batch_slice],
},
on_unused_input='ignore',
)
iter_valid = None
if self.use_valid:
iter_valid = theano.function(
[batch_index], [loss_eval, accuracy, proba],
givens={
X_batch: dataset['X_valid'][batch_slice],
y_batch: dataset['y_valid'][batch_slice],
},
)
return dict(train=iter_train, valid=iter_valid)
Example #4
| Source File: nn_adagrad.py From kaggle_otto with BSD 3-Clause "New" or "Revised" License | 5 votes |
|
def create_iter_functions(self, dataset, output_layer, X_tensor_type=T.matrix):
batch_index = T.iscalar('batch_index')
X_batch = X_tensor_type('x')
y_batch = T.ivector('y')
batch_slice = slice(batch_index * self.batch_size, (batch_index + 1) * self.batch_size)
objective = Objective(output_layer, loss_function=categorical_crossentropy)
loss_train = objective.get_loss(X_batch, target=y_batch)
loss_eval = objective.get_loss(X_batch, target=y_batch, deterministic=True)
pred = T.argmax(output_layer.get_output(X_batch, deterministic=True), axis=1)
proba = output_layer.get_output(X_batch, deterministic=True)
accuracy = T.mean(T.eq(pred, y_batch), dtype=theano.config.floatX)
all_params = get_all_params(output_layer)
updates = adagrad(loss_train, all_params, self.lr, self.epsilon)
iter_train = theano.function(
[batch_index], loss_train,
updates=updates,
givens={
X_batch: dataset['X_train'][batch_slice],
y_batch: dataset['y_train'][batch_slice],
},
on_unused_input='ignore',
)
iter_valid = None
if self.use_valid:
iter_valid = theano.function(
[batch_index], [loss_eval, accuracy, proba],
givens={
X_batch: dataset['X_valid'][batch_slice],
y_batch: dataset['y_valid'][batch_slice],
},
)
return dict(train=iter_train, valid=iter_valid)
Example #5
| Source File: stack.py From kaggle-avito with MIT License | 5 votes |
|
def get_nn_model(shape):
np.random.seed(9)
model = NeuralNet(
layers=[
('input', layers.InputLayer),
('hidden1', layers.DenseLayer),
('hidden2', layers.DenseLayer),
('output', layers.DenseLayer),
],
input_shape=(None, shape[1]),
hidden1_num_units=16, # number of units in hidden layer
hidden1_nonlinearity=sigmoid,
hidden2_num_units=8, # number of units in hidden layer
hidden2_nonlinearity=sigmoid,
output_nonlinearity=softmax,
output_num_units=2, # target values
# optimization method:
update=adagrad,
update_learning_rate=theano.shared(np.float32(0.1)),
on_epoch_finished=[
],
use_label_encoder=False,
batch_iterator_train=BatchIterator(batch_size=500),
regression=False, # flag to indicate we're dealing with regression problem
max_epochs=900, # we want to train this many epochs
verbose=1,
eval_size=0.0,
)
return model
Example #6
| Source File: neuralforest.py From ShallowNeuralDecisionForest with MIT License | 4 votes |
|
def __init__(self, n_inputs, n_outputs, regression, multiclass=False, depth=5, n_estimators=20, n_hidden=128, learning_rate=0.01, num_epochs=500, pi_iters=20, sgd_iters=10, batch_size=1000, momentum=0.0, dropout=0.0, loss=None, update=adagrad):
"""
Parameters
----------
n_inputs : number of input features
n_outputs : number of classes to predict (1 for regression)
for 2 class classification n_outputs should be 2, not 1
regression : True for regression, False for classification
multiclass : not used
depth : depth of each tree in the ensemble
n_estimators : number of trees in the ensemble
n_hidden : number of neurons in the hidden layer
pi_iters : number of iterations for the iterative algorithm that updates pi
sgd_iters : number of full iterations of sgd between two consequtive updates of pi
loss : theano loss function. If None, squared error will be used for regression and
cross entropy will be used for classification
update : theano update function
"""
self._depth = depth
self._n_estimators = n_estimators
self._n_hidden = n_hidden
self._n_outputs = n_outputs
self._loss = loss
self._regression = regression
self._multiclass = multiclass
self._learning_rate = learning_rate
self._num_epochs = num_epochs
self._pi_iters = pi_iters
self._sgd_iters = sgd_iters
self._batch_size = batch_size
self._momentum = momentum
self._update = update
self.t_input = T.matrix('input')
self.t_label = T.matrix('output')
self._cached_trainable_params = None
self._cached_params = None
self._n_net_out = n_estimators * ((1 << depth) - 1)
self.l_input = InputLayer((None, n_inputs))
self.l_dense1 = DenseLayer(self.l_input, self._n_hidden, nonlinearity=rectify)
if dropout != 0:
self.l_dense1 = DropoutLayer(self.l_dense1, p=dropout)
if not __DEBUG_NO_FOREST__:
self.l_dense2 = DenseLayer(self.l_dense1, self._n_net_out, nonlinearity=sigmoid)
self.l_forest = NeuralForestLayer(self.l_dense2, self._depth, self._n_estimators, self._n_outputs, self._pi_iters)
else:
self.l_forest = DenseLayer(self.l_dense1, self._n_outputs, nonlinearity=softmax)
Example #7
| Source File: updates.py From Deep-SVDD with MIT License | 4 votes |
|
def get_updates(nnet,
train_obj,
trainable_params,
solver=None):
implemented_solvers = ("sgd", "momentum", "nesterov", "adagrad", "rmsprop", "adadelta", "adam", "adamax")
if solver not in implemented_solvers:
nnet.sgd_solver = "adam"
else:
nnet.sgd_solver = solver
if nnet.sgd_solver == "sgd":
updates = l_updates.sgd(train_obj,
trainable_params,
learning_rate=Cfg.learning_rate)
elif nnet.sgd_solver == "momentum":
updates = l_updates.momentum(train_obj,
trainable_params,
learning_rate=Cfg.learning_rate,
momentum=Cfg.momentum)
elif nnet.sgd_solver == "nesterov":
updates = l_updates.nesterov_momentum(train_obj,
trainable_params,
learning_rate=Cfg.learning_rate,
momentum=Cfg.momentum)
elif nnet.sgd_solver == "adagrad":
updates = l_updates.adagrad(train_obj,
trainable_params,
learning_rate=Cfg.learning_rate)
elif nnet.sgd_solver == "rmsprop":
updates = l_updates.rmsprop(train_obj,
trainable_params,
learning_rate=Cfg.learning_rate,
rho=Cfg.rho)
elif nnet.sgd_solver == "adadelta":
updates = l_updates.adadelta(train_obj,
trainable_params,
learning_rate=Cfg.learning_rate,
rho=Cfg.rho)
elif nnet.sgd_solver == "adam":
updates = l_updates.adam(train_obj,
trainable_params,
learning_rate=Cfg.learning_rate)
elif nnet.sgd_solver == "adamax":
updates = l_updates.adamax(train_obj,
trainable_params,
learning_rate=Cfg.learning_rate)
return updates
