Did I find the right examples for you? yes no      Crawl my project      Python Jobs

All Samples(16)  |  Call(8)  |  Derive(1)  |  Import(7)

src/p/y/pylearn2-HEAD/pylearn2/models/mlp.py   pylearn2(Download)
from pylearn2.expr.probabilistic_max_pooling import max_pool_channels
from pylearn2.linear import conv2d
from pylearn2.linear.matrixmul import MatrixMul
from pylearn2.models.model import Model
from pylearn2.monitor import get_monitor_doc
        W.name = self.layer_name + '_W'
 
        self.transformer = MatrixMul(W)
 
        W, = self.transformer.get_params()
        W.name = self.layer_name + '_W'
 
        self.transformer = MatrixMul(W)
 
        W, = self.transformer.get_params()

src/p/y/pylearn2-HEAD/pylearn2/models/dbm/layer.py   pylearn2(Download)
from pylearn2.linear.conv2d import make_random_conv2D, make_sparse_random_conv2D
from pylearn2.linear.conv2d_c01b import setup_detector_layer_c01b
from pylearn2.linear.matrixmul import MatrixMul
from pylearn2.models import Model
from pylearn2.models.dbm import init_sigmoid_bias_from_marginals
        W.name = self.layer_name + '_W'
 
        self.transformer = MatrixMul(W)
 
        W ,= self.transformer.get_params()

src/p/y/pylearn2-HEAD/pylearn2/models/dbm/ising.py   pylearn2(Download)
 
from pylearn2.expr.nnet import sigmoid_numpy
from pylearn2.linear.matrixmul import MatrixMul
from pylearn2.models.dbm import init_sigmoid_bias_from_array
from pylearn2.models.dbm.layer import HiddenLayer, VisibleLayer
        W.name = self.layer_name + '_W'
 
        self.transformer = MatrixMul(W)
 
        W, = self.transformer.get_params()

src/p/y/pylearn2-HEAD/pylearn2/models/rbm.py   pylearn2(Download)
from pylearn2.models import Model
from pylearn2.expr.nnet import inverse_sigmoid_numpy
from pylearn2.linear.matrixmul import MatrixMul
from pylearn2.space import VectorSpace
from pylearn2.utils import safe_union
                                nhid).T
 
                self.transformer = MatrixMul(  sharedX(
                        W,
                        name='W',

src/p/y/pylearn2-HEAD/pylearn2/models/maxout.py   pylearn2(Download)
from theano import tensor as T
 
from pylearn2.linear.matrixmul import MatrixMul
from pylearn2.models.mlp import Layer
from pylearn2.models.model import Model
        W.name = self.layer_name + '_W'
 
        self.transformer = MatrixMul(W)
 
        W, = self.transformer.get_params()

src/p/y/pylearn2-HEAD/pylearn2/sandbox/nlp/linear/matrixmul.py   pylearn2(Download)
class MatrixMul(matrixmul.MatrixMul):
    """
    Operations which can be represented as matrix multiplications.
 
    Parameters

src/p/y/pylearn2-HEAD/pylearn2/linear/tests/test_matrixmul.py   pylearn2(Download)
from pylearn2.linear.matrixmul import MatrixMul, make_local_rfs
from pylearn2.datasets.dense_design_matrix import DefaultViewConverter
from pylearn2.datasets.dense_design_matrix import DenseDesignMatrix
import theano
from theano import tensor
        return theano.shared(theano._asarray(value, dtype=dtype))
    tensor_W = [sharedW(W, dtype) for W in np_W]
    matrixmul = [MatrixMul(W) for W in tensor_W]
    assert all(mm.get_params()[0] == W for mm, W in zip(matrixmul, tensor_W))
 

src/p/y/pylearn2-HEAD/pylearn2/energy_functions/tests/test_rbm_energy.py   pylearn2(Download)
from pylearn2.utils import as_floatX
from pylearn2.utils import sharedX
from pylearn2.linear.matrixmul import MatrixMul
 
test_m = 2
sigma.tag.test_value = vsigma
 
E = GRBM_Type_1(transformer=MatrixMul(W), bias_vis=bv,
                bias_hid=bh, sigma=sigma)