本文整理汇总了Python中theano.tensor.add方法的典型用法代码示例。如果您正苦于以下问题:Python tensor.add方法的具体用法?Python tensor.add怎么用?Python tensor.add使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类theano.tensor
的用法示例。
在下文中一共展示了tensor.add方法的15个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: build_bilinear_net
# 需要导入模块: from theano import tensor [as 别名]
# 或者: from theano.tensor import add [as 别名]
def build_bilinear_net(input_shapes, X_var=None, U_var=None, X_diff_var=None, axis=1):
x_shape, u_shape = input_shapes
X_var = X_var or T.tensor4('X')
U_var = U_var or T.matrix('U')
X_diff_var = X_diff_var or T.tensor4('X_diff')
X_next_var = X_var + X_diff_var
l_x = L.InputLayer(shape=(None,) + x_shape, input_var=X_var)
l_u = L.InputLayer(shape=(None,) + u_shape, input_var=U_var)
l_x_diff_pred = LT.BilinearLayer([l_x, l_u], axis=axis)
l_x_next_pred = L.ElemwiseMergeLayer([l_x, l_x_diff_pred], T.add)
l_y = L.flatten(l_x)
l_y_diff_pred = L.flatten(l_x_diff_pred)
X_next_pred_var = lasagne.layers.get_output(l_x_next_pred)
loss = ((X_next_var - X_next_pred_var) ** 2).mean(axis=0).sum() / 2.
net_name = 'BilinearNet'
input_vars = OrderedDict([(var.name, var) for var in [X_var, U_var, X_diff_var]])
pred_layers = OrderedDict([('y_diff_pred', l_y_diff_pred), ('y', l_y), ('x0_next_pred', l_x_next_pred)])
return net_name, input_vars, pred_layers, loss
示例2: create_structure
# 需要导入模块: from theano import tensor [as 别名]
# 或者: from theano.tensor import add [as 别名]
def create_structure(self):
"""Creates the symbolic graph of this layer.
Sets self.output to a symbolic matrix that describes the output of this
layer. If the inputs are the same size as the output, the output will be
the elementwise sum of the inputs. If needed, the inputs will be
projected to the same size.
"""
for input_index, input_layer in enumerate(self._input_layers):
input_size = input_layer.output_size
if input_size == self.output_size:
input_matrix = input_layer.output
else:
input_matrix = self._tensor_preact(input_layer.output,
'input{}'.format(input_index),
use_bias=False)
if self.output is None:
self.output = input_matrix
else:
self.output = tensor.add(self.output, input_matrix)
示例3: rbf_kernel
# 需要导入模块: from theano import tensor [as 别名]
# 或者: from theano.tensor import add [as 别名]
def rbf_kernel(X):
XY = T.dot(X, X.T)
x2 = T.sum(X**2, axis=1).dimshuffle(0, 'x')
X2e = T.repeat(x2, X.shape[0], axis=1)
H = X2e + X2e.T - 2. * XY
V = H.flatten()
# median distance
h = T.switch(T.eq((V.shape[0] % 2), 0),
# if even vector
T.mean(T.sort(V)[ ((V.shape[0] // 2) - 1) : ((V.shape[0] // 2) + 1) ]),
# if odd vector
T.sort(V)[V.shape[0] // 2])
h = T.sqrt(.5 * h / T.log(H.shape[0].astype('float32') + 1.))
# compute the rbf kernel
kxy = T.exp(-H / (h ** 2) / 2.0)
dxkxy = -T.dot(kxy, X)
sumkxy = T.sum(kxy, axis=1).dimshuffle(0, 'x')
dxkxy = T.add(dxkxy, T.mul(X, sumkxy)) / (h ** 2)
return kxy, dxkxy
示例4: input_to_h_from_v
# 需要导入模块: from theano import tensor [as 别名]
# 或者: from theano.tensor import add [as 别名]
def input_to_h_from_v(self, v):
"""
.. todo::
WRITEME
"""
D = self.Lambda
alpha = self.alpha
def sum_s(x):
return x.reshape((
-1,
self.nhid,
self.n_s_per_h)).sum(axis=2)
return tensor.add(
self.b,
-0.5 * tensor.dot(v * v, D),
sum_s(self.mu * tensor.dot(v, self.W)),
sum_s(0.5 * tensor.sqr(tensor.dot(v, self.W)) / alpha))
#def mean_h_given_v(self, v):
# inherited version is OK:
# return nnet.sigmoid(self.input_to_h_from_v(v))
示例5: free_energy_given_v
# 需要导入模块: from theano import tensor [as 别名]
# 或者: from theano.tensor import add [as 别名]
def free_energy_given_v(self, v):
"""
.. todo::
WRITEME
"""
sigmoid_arg = self.input_to_h_from_v(v)
return tensor.add(
0.5 * (self.B * (v ** 2)).sum(axis=1),
-tensor.nnet.softplus(sigmoid_arg).sum(axis=1))
#def __call__(self, v):
# inherited version is OK
#def reconstruction_error:
# inherited version should be OK
#def params(self):
# inherited version is OK.
示例6: sequence_iteration
# 需要导入模块: from theano import tensor [as 别名]
# 或者: from theano.tensor import add [as 别名]
def sequence_iteration(self, output, mask,use_dropout=0,dropout_value=0.5):
dot_product = T.dot(output , self.t_w_out)
net_o = T.add( dot_product , self.t_b_out )
ex_net = T.exp(net_o)
sum_net = T.sum(ex_net, axis=2, keepdims=True)
softmax_o = ex_net / sum_net
mask = T.addbroadcast(mask, 2) # to do nesseccary?
output = T.mul(mask, softmax_o) + T.mul( (1. - mask) , 1e-6 )
return output #result
###### Linear Layer
########################################
示例7: sequence_iteration
# 需要导入模块: from theano import tensor [as 别名]
# 或者: from theano.tensor import add [as 别名]
def sequence_iteration(self, in_seq, mask, use_dropout,dropout_value=1):
in_seq_d = T.switch(use_dropout,
(in_seq *
self.trng.binomial(in_seq.shape,
p=dropout_value, n=1,
dtype=in_seq.dtype)),
in_seq)
rz_in_seq = T.add( T.dot(in_seq_d, self.weights[0]) , self.weights[1] )
out_seq, updates = theano.scan(
fn=self.t_forward_step,
sequences=[mask, rz_in_seq], # in_seq_d],
outputs_info=[self.t_ol_t00],
non_sequences=[i for i in self.weights][2:] + [self.t_n_out],
go_backwards = self.go_backwards,
truncate_gradient=-1,
#n_steps=50,
strict=True,
allow_gc=False,
)
return out_seq
示例8: fit
# 需要导入模块: from theano import tensor [as 别名]
# 或者: from theano.tensor import add [as 别名]
def fit(self, weights, o_error, tpo ):
gradients = T.grad(o_error ,weights)
updates = []
for c, v, w, g in zip(self.t_cache, self.t_velocity, weights,gradients):
new_velocity = T.sub( T.mul(tpo["momentum_rate"], v) , T.mul(tpo["learn_rate"], g) )
new_cache = T.add( T.mul(tpo["decay_rate"] , c) , T.mul(T.sub( 1, tpo["decay_rate"]) , T.sqr(g)))
new_weights = T.sub(T.add(w , new_velocity) , T.true_div( T.mul(g,tpo["learn_rate"]) , T.sqrt(T.add(new_cache,0.1**8))))
updates.append((w, new_weights))
updates.append((v, new_velocity))
updates.append((c, new_cache))
return updates
###### Nesterov momentum
########################################
示例9: __init__
# 需要导入模块: from theano import tensor [as 别名]
# 或者: from theano.tensor import add [as 别名]
def __init__(self, net, mixfrac=1.0, maxiter=25):
EzPickle.__init__(self, net, mixfrac, maxiter)
self.net = net
self.mixfrac = mixfrac
x_nx = net.input
self.predict = theano.function([x_nx], net.output, **FNOPTS)
ypred_ny = net.output
ytarg_ny = T.matrix("ytarg")
var_list = net.trainable_weights
l2 = 1e-3 * T.add(*[T.square(v).sum() for v in var_list])
N = x_nx.shape[0]
mse = T.sum(T.square(ytarg_ny - ypred_ny))/N
symb_args = [x_nx, ytarg_ny]
loss = mse + l2
self.opt = LbfgsOptimizer(loss, var_list, symb_args, maxiter=maxiter, extra_losses={"mse":mse, "l2":l2})
示例10: __add__
# 需要导入模块: from theano import tensor [as 别名]
# 或者: from theano.tensor import add [as 别名]
def __add__(left, right):
return add(left, right)
示例11: __radd__
# 需要导入模块: from theano import tensor [as 别名]
# 或者: from theano.tensor import add [as 别名]
def __radd__(right, left):
return add(left, right)
示例12: test_softmax_optimizations_w_bias2
# 需要导入模块: from theano import tensor [as 别名]
# 或者: from theano.tensor import add [as 别名]
def test_softmax_optimizations_w_bias2(self):
x = tensor.matrix('x')
b = tensor.vector('b')
c = tensor.vector('c')
one_of_n = tensor.lvector('one_of_n')
op = crossentropy_categorical_1hot
fgraph = gof.FunctionGraph(
[x, b, c, one_of_n],
[op(softmax_op(T.add(x, b, c)), one_of_n)])
assert fgraph.outputs[0].owner.op == op
# print 'BEFORE'
# for node in fgraph.toposort():
# print node.op
# print '----'
theano.compile.mode.optdb.query(
theano.compile.mode.OPT_FAST_RUN).optimize(fgraph)
# print 'AFTER'
# for node in fgraph.toposort():
# print node.op
# print '===='
assert len(fgraph.toposort()) == 3
assert str(fgraph.outputs[0].owner.op) == 'OutputGuard'
assert (fgraph.outputs[0].owner.inputs[0].owner.op ==
crossentropy_softmax_argmax_1hot_with_bias)
示例13: set_layer_param_tags
# 需要导入模块: from theano import tensor [as 别名]
# 或者: from theano.tensor import add [as 别名]
def set_layer_param_tags(layer, params=None, **tags):
"""
If params is None, update tags of all parameters, else only update tags of parameters in params.
"""
for param, param_tags in layer.params.items():
if params is None or param in params:
for tag, value in tags.items():
if value:
param_tags.add(tag)
else:
param_tags.discard(tag)
示例14: __init__
# 需要导入模块: from theano import tensor [as 别名]
# 或者: from theano.tensor import add [as 别名]
def __init__(self, incomings, **kwargs):
super(BatchwiseSumLayer, self).__init__(incomings, T.add, **kwargs)
示例15: __init__
# 需要导入模块: from theano import tensor [as 别名]
# 或者: from theano.tensor import add [as 别名]
def __init__(self, x, y, args):
self.params_theta = []
self.params_lambda = []
self.params_weight = []
if args.dataset == 'mnist':
input_size = (None, 1, 28, 28)
elif args.dataset == 'cifar10':
input_size = (None, 3, 32, 32)
else:
raise AssertionError
layers = [ll.InputLayer(input_size)]
self.penalty = theano.shared(np.array(0.))
#conv1
layers.append(Conv2DLayerWithReg(args, layers[-1], 20, 5))
self.add_params_to_self(args, layers[-1])
layers.append(ll.MaxPool2DLayer(layers[-1], pool_size=2, stride=2))
#conv1
layers.append(Conv2DLayerWithReg(args, layers[-1], 50, 5))
self.add_params_to_self(args, layers[-1])
layers.append(ll.MaxPool2DLayer(layers[-1], pool_size=2, stride=2))
#fc1
layers.append(DenseLayerWithReg(args, layers[-1], num_units=500))
self.add_params_to_self(args, layers[-1])
#softmax
layers.append(DenseLayerWithReg(args, layers[-1], num_units=10, nonlinearity=nonlinearities.softmax))
self.add_params_to_self(args, layers[-1])
self.layers = layers
self.y = ll.get_output(layers[-1], x, deterministic=False)
self.prediction = T.argmax(self.y, axis=1)
# self.penalty = penalty if penalty != 0. else T.constant(0.)
print(self.params_lambda)
# time.sleep(20)
# cost function
self.loss = T.mean(categorical_crossentropy(self.y, y))
self.lossWithPenalty = T.add(self.loss, self.penalty)
print "loss and losswithpenalty", type(self.loss), type(self.lossWithPenalty)