示例#1
0
                                  wordvectors,
                                  t2ind,
                                  n_targets,
                                  upto=-1,
                                  ds='test',
                                  binoutvec=True)

# train network
rng = numpy.random.RandomState(23455)
if usetypecosine:
    print 'using cosine(e,t) as another input feature'
    typevecmatrix = utils.buildtypevecmatrix(
        t2ind, wordvectors, vectorsize)  # a matrix with size: 102 * dim
    e2simmatrix_test = utils.buildcosinematrix(input_matrix_test,
                                               typevecmatrix)
    input_matrix_test = utils.extend_in_matrix(input_matrix_test,
                                               e2simmatrix_test)

dt = theano.config.floatX  # @UndefinedVariable

index = T.lscalar()  # index to a [mini]batch
x = T.matrix('x')  # the data is presented as rasterized images
y = T.imatrix('y')  # the labels are presented as 1D vector of
# [int] labels
######################
# BUILD ACTUAL MODEL #
######################
print '... building the model'
rng = numpy.random.RandomState(23455)
layer1 = layers.HiddenLayer(rng,
                            input=x,
                            n_in=input_matrix_test.shape[1],
示例#2
0
use_tanh_out = False
outputtype = config['outtype'] #hinge or softmax
usetypecosine = False
if 'typecosine' in config:
    usetypecosine = utils.str_to_bool(config['typecosine'])

(t2ind, n_targets, wordvectors, vectorsize, typefreq_traindev) = utils.loadTypesAndVectors(targetTypesFile, vectorFile)
(rvt, input_matrix_test, iet,resvectstnall, ntrn) = utils.fillOnlyEntityData(testfile,vectorsize, wordvectors, t2ind, n_targets, upto=-1, ds='test', binoutvec=True)

# train network
rng = numpy.random.RandomState(23455)
if usetypecosine:
    print 'using cosine(e,t) as another input feature'
    typevecmatrix = utils.buildtypevecmatrix(t2ind, wordvectors, vectorsize) # a matrix with size: 102 * dim 
    e2simmatrix_test = utils.buildcosinematrix(input_matrix_test, typevecmatrix)
    input_matrix_test = utils.extend_in_matrix(input_matrix_test, e2simmatrix_test)

dt = theano.config.floatX  # @UndefinedVariable

index = T.lscalar()  # index to a [mini]batch
x = T.matrix('x')  # the data is presented as rasterized images
y = T.imatrix('y')  # the labels are presented as 1D vector of
                        # [int] labels
######################
# BUILD ACTUAL MODEL #
######################
print '... building the model'
rng = numpy.random.RandomState(23455)
layer1 = layers.HiddenLayer(rng, input=x, n_in=input_matrix_test.shape[1],n_out=num_of_hidden_units, activation=T.tanh)

outlayers = []
示例#3
0
    
upto = -1
(t2ind, n_targets, wordvectors, vectorsize, typefreq_traindev) = utils.loadTypesAndVectors(targetTypesFile, vectorFile, upto=upto)

(rvt, input_matrix_train, iet,resvectrnall, ntrn) = utils.fillOnlyEntityData(trainfile,vectorsize, wordvectors, t2ind, n_targets, upto=upto, binoutvec=True)
print "number of training examples:" + str(len(iet))

(rvd, input_matrix_dev, ied,resvecdevall, ntdev) = utils.fillOnlyEntityData(devfile,vectorsize, wordvectors, t2ind, n_targets, upto=upto, binoutvec=True)
print "number of validation examples:" +  str(len(ied))

if usetypecosine:
    print 'using cosine(e,t) as another input feature'
    typevecmatrix = utils.buildtypevecmatrix(t2ind, wordvectors, vectorsize) # a matrix with size: 102 * dim 
    e2simmatrix_train = utils.buildcosinematrix(input_matrix_train, typevecmatrix)
    e2simmatrix_dev = utils.buildcosinematrix(input_matrix_dev, typevecmatrix)
    input_matrix_train = utils.extend_in_matrix(input_matrix_train, e2simmatrix_train)
    input_matrix_dev = utils.extend_in_matrix(input_matrix_dev, e2simmatrix_dev)

rng = numpy.random.RandomState(23455)

dt = theano.config.floatX  # @UndefinedVariable
train_set_x = theano.shared(numpy.matrix(input_matrix_train, dtype=dt))  # @UndefinedVariable
valid_set_x = theano.shared(numpy.matrix(input_matrix_dev, dtype=dt))
train_set_y = theano.shared(numpy.matrix(resvectrnall, dtype=numpy.dtype(numpy.int32)))
valid_set_y = theano.shared(numpy.matrix(resvecdevall, dtype=numpy.dtype(numpy.int32)))

n_train_batches = train_set_x.get_value(borrow=True).shape[0]
n_valid_batches = valid_set_x.get_value(borrow=True).shape[0]
n_train_batches /= batch_size
n_valid_batches /= batch_size