Python theano.tensor.shape() Examples

def perform(self, node, inputs, outputs):
        (x_data, x_indices, x_indptr, x_shape,
         g_data, g_indices, g_indptr, g_shape) = inputs
        (g_out,) = outputs
        if len(x_indptr) - 1 == x_shape[0]:
            sp_dim = x_shape[1]
        else:
            sp_dim = x_shape[0]

        g_row = numpy.zeros(sp_dim, dtype=g_data.dtype)
        gout_data = numpy.zeros(x_data.shape, dtype=node.outputs[0].dtype)

        for i in range(len(x_indptr) - 1):
            for j_ptr in range(g_indptr[i], g_indptr[i + 1]):
                g_row[g_indices[j_ptr]] += g_data[j_ptr]

            for j_ptr in range(x_indptr[i], x_indptr[i + 1]):
                gout_data[j_ptr] = g_row[x_indices[j_ptr]]

            for j_ptr in range(g_indptr[i], g_indptr[i + 1]):
                g_row[g_indices[j_ptr]] = 0

        g_out[0] = gout_data 

def structured_monoid(tensor_op):
    # Generic operation to perform many kinds of monoid element-wise
    # operations on the non-zeros of a sparse matrix.

    # The first parameter must always be a sparse matrix. The other parameters
    # must be scalars which will be passed as argument to the tensor_op.

    def decorator(f):
        def wrapper(*args):
            x = as_sparse_variable(args[0])
            assert x.format in ["csr", "csc"]

            xs = [scalar.as_scalar(arg) for arg in args[1:]]

            data, ind, ptr, shape = csm_properties(x)

            data = tensor_op(data, *xs)

            return CSM(x.format)(data, ind, ptr, shape)
        wrapper.__name__ = str(tensor_op.scalar_op)
        return wrapper
    return decorator 

def perform(self, node, inputs, outputs):
        (a_indices, a_indptr, b, g_ab) = inputs
        (out,) = outputs
        g_a_data = numpy.zeros(a_indices.shape, dtype=g_ab.dtype)
        for j in xrange(len(a_indptr) - 1):
            ind0 = a_indptr[j]
            ind1 = a_indptr[j + 1]
            for i_idx in xrange(ind0, ind1):
                i = a_indices[i_idx]
                # Depending on the type of g_ab and b (sparse or dense),
                # the following dot product can result in a scalar or
                # a (1, 1) sparse matrix.
                dot_val = numpy.dot(g_ab[i], b[j].T)
                if isinstance(dot_val, scipy.sparse.spmatrix):
                    dot_val = dot_val[0, 0]
                g_a_data[i_idx] = dot_val
        out[0] = g_a_data 

def perform(self, node, inputs, outputs):
        (a_indices, a_indptr, b, g_ab) = inputs
        (out,) = outputs
        g_a_data = numpy.zeros(a_indices.shape, dtype=g_ab.dtype)
        for i in xrange(len(a_indptr) - 1):  # loop over rows
            ind0 = a_indptr[i]
            ind1 = a_indptr[i + 1]
            # loop over values in that row (columns)
            for j_idx in xrange(ind0, ind1):
                j = a_indices[j_idx]
                # grad is dot product of i-th row of gradient with j-th row of b
                # Depending on the type of g_ab and b (sparse or dense),
                # the following dot product can result in a scalar or
                # a (1, 1) sparse matrix.
                dot_val = numpy.dot(g_ab[i], b[j].T)
                if isinstance(dot_val, scipy.sparse.spmatrix):
                    dot_val = dot_val[0, 0]
                g_a_data[j_idx] = dot_val
        out[0] = g_a_data 

def setup_transform_net(self, input_var=None):
		transform_net = InputLayer(shape=self.shape, input_var=input_var)
		transform_net = style_conv_block(transform_net, self.num_styles, 32, 9, 1)
		transform_net = style_conv_block(transform_net, self.num_styles, 64, 3, 2)
		transform_net = style_conv_block(transform_net, self.num_styles, 128, 3, 2)
		for _ in range(5):
			transform_net = residual_block(transform_net, self.num_styles)
		transform_net = nn_upsample(transform_net, self.num_styles)
		transform_net = nn_upsample(transform_net, self.num_styles)

		if self.net_type == 0:
			transform_net = style_conv_block(transform_net, self.num_styles, 3, 9, 1, tanh)
			transform_net = ExpressionLayer(transform_net, lambda X: 150.*X, output_shape=None)
		elif self.net_type == 1:
			transform_net = style_conv_block(transform_net, self.num_styles, 3, 9, 1, sigmoid)

		self.network['transform_net'] = transform_net 

def __init__(self, input_var=None, num_styles=None, shape=(None, 3, 256, 256), net_type=1, **kwargs):
		"""
		net_type: 0 (fast neural style- fns) or 1 (conditional instance norm- cin)
		"""
		assert net_type in [0, 1]
		self.net_type = net_type
		self.network = {}

		if len(shape) == 2:
			shape=(None, 3, shape[0], shape[1])
		elif len(shape) == 3:
			shape=(None, shape[0], shape[1], shape[2])
		self.shape = shape

		self.num_styles = num_styles

		self.network['loss_net'] = {}
		self.setup_loss_net()
		self.load_loss_net_weights()

		self.network['transform_net'] = {}
		self.setup_transform_net(input_var) 

def grad(self, inputs, gout):
        (gz,) = gout
        is_continuous = [(inputs[i].dtype in tensor.continuous_dtypes)
                         for i in range(len(inputs))]

        if _is_sparse_variable(gz):
            gz = dense_from_sparse(gz)

        split = tensor.Split(len(inputs))(gz, 0,
                                          tensor.stack(
                                              [x.shape[0]
                                               for x in inputs]))
        if not isinstance(split, list):
            split = [split]

        derivative = [SparseFromDense(self.format)(s) for s in split]

        def choose(continuous, derivative):
            if continuous:
                return derivative
            else:
                return None
        return [choose(c, d) for c, d in zip(is_continuous, derivative)] 

def grad(self, inputs, gout):
        (gz,) = gout
        is_continuous = [(inputs[i].dtype in tensor.continuous_dtypes)
                         for i in range(len(inputs))]

        if _is_sparse_variable(gz):
            gz = dense_from_sparse(gz)

        split = tensor.Split(len(inputs))(gz, 0,
                                          tensor.stack(
                                              [x.shape[0]
                                               for x in inputs]))
        if not isinstance(split, list):
            split = [split]

        derivative = [SparseFromDense(self.format)(s) for s in split]

        def choose(continuous, derivative):
            if continuous:
                return derivative
            else:
                return None
        return [choose(c, d) for c, d in zip(is_continuous, derivative)] 

def perform(self, node, inputs, outputs):
        (x, s) = inputs
        (z,) = outputs
        M, N = x.shape
        assert x.format == 'csc'
        assert s.shape == (M,)

        indices = x.indices
        indptr = x.indptr

        y_data = x.data.copy()

        for j in xrange(0, N):
            for i_idx in xrange(indptr[j], indptr[j + 1]):
                y_data[i_idx] *= s[indices[i_idx]]

        z[0] = scipy.sparse.csc_matrix((y_data, indices, indptr), (M, N)) 

def perform(self, node, inputs, outputs):
        (x, s) = inputs
        (z,) = outputs
        M, N = x.shape
        assert x.format == 'csc'
        assert s.shape == (M,)

        indices = x.indices
        indptr = x.indptr

        y_data = x.data.copy()

        for j in xrange(0, N):
            for i_idx in xrange(indptr[j], indptr[j + 1]):
                y_data[i_idx] *= s[indices[i_idx]]

        z[0] = scipy.sparse.csc_matrix((y_data, indices, indptr), (M, N)) 

def structured_monoid(tensor_op):
    # Generic operation to perform many kinds of monoid element-wise
    # operations on the non-zeros of a sparse matrix.

    # The first parameter must always be a sparse matrix. The other parameters
    # must be scalars which will be passed as argument to the tensor_op.

    def decorator(f):
        def wrapper(*args):
            x = as_sparse_variable(args[0])
            assert x.format in ["csr", "csc"]

            xs = [scalar.as_scalar(arg) for arg in args[1:]]

            data, ind, ptr, shape = csm_properties(x)

            data = tensor_op(data, *xs)

            return CSM(x.format)(data, ind, ptr, shape)
        wrapper.__name__ = str(tensor_op.scalar_op)
        return wrapper
    return decorator 

def perform(self, node, inputs, outputs):
        # for efficiency, if remap does nothing, then do not apply it
        (data, indices, indptr, shape) = inputs
        (out,) = outputs

        if len(shape) != 2:
            raise ValueError('Shape should be an array of length 2')
        if data.shape != indices.shape:
            errmsg = ('Data (shape ' + repr(data.shape) +
                      ' must have the same number of elements ' +
                      'as indices (shape' + repr(indices.shape) +
                      ')')
            raise ValueError(errmsg)
        if self.format == 'csc':
            out[0] = scipy.sparse.csc_matrix((data, indices.copy(),
                                              indptr.copy()),
                                             numpy.asarray(shape), copy=False)
        else:
            assert self.format == 'csr'
            out[0] = scipy.sparse.csr_matrix((data, indices.copy(),
                                              indptr.copy()), shape.copy(),
                                             copy=False) 

def sp_ones_like(x):
    """
    Construct a sparse matrix of ones with the same sparsity pattern.

    Parameters
    ----------
    x
        Sparse matrix to take the sparsity pattern.

    Returns
    -------
    A sparse matrix
        The same as `x` with data changed for ones.

    """
    # TODO: don't restrict to CSM formats
    data, indices, indptr, shape = csm_properties(x)
    return CSM(format=x.format)(tensor.ones_like(data), indices, indptr, shape) 

def sp_zeros_like(x):
    """
    Construct a sparse matrix of zeros.

    Parameters
    ----------
    x
        Sparse matrix to take the shape.

    Returns
    -------
    A sparse matrix
        The same as `x` with zero entries for all element.

    """

    # TODO: don't restrict to CSM formats
    _, _, indptr, shape = csm_properties(x)
    return CSM(format=x.format)(data=numpy.array([], dtype=x.type.dtype),
                                indices=numpy.array([], dtype='int32'),
                                indptr=tensor.zeros_like(indptr),
                                shape=shape) 

def perform(self, node, inputs, outputs):
        (a_indices, a_indptr, b, g_ab) = inputs
        (out,) = outputs
        g_a_data = numpy.zeros(a_indices.shape, dtype=g_ab.dtype)
        for j in xrange(len(a_indptr) - 1):
            ind0 = a_indptr[j]
            ind1 = a_indptr[j + 1]
            for i_idx in xrange(ind0, ind1):
                i = a_indices[i_idx]
                # Depending on the type of g_ab and b (sparse or dense),
                # the following dot product can result in a scalar or
                # a (1, 1) sparse matrix.
                dot_val = numpy.dot(g_ab[i], b[j].T)
                if isinstance(dot_val, scipy.sparse.spmatrix):
                    dot_val = dot_val[0, 0]
                g_a_data[i_idx] = dot_val
        out[0] = g_a_data 

def perform(self, node, inputs, outputs):
        (a_indices, a_indptr, b, g_ab) = inputs
        (out,) = outputs
        g_a_data = numpy.zeros(a_indices.shape, dtype=g_ab.dtype)
        for i in xrange(len(a_indptr) - 1):  # loop over rows
            ind0 = a_indptr[i]
            ind1 = a_indptr[i + 1]
            # loop over values in that row (columns)
            for j_idx in xrange(ind0, ind1):
                j = a_indices[j_idx]
                # grad is dot product of i-th row of gradient with j-th row of b
                # Depending on the type of g_ab and b (sparse or dense),
                # the following dot product can result in a scalar or
                # a (1, 1) sparse matrix.
                dot_val = numpy.dot(g_ab[i], b[j].T)
                if isinstance(dot_val, scipy.sparse.spmatrix):
                    dot_val = dot_val[0, 0]
                g_a_data[j_idx] = dot_val
        out[0] = g_a_data 

def sp_zeros_like(x):
    """
    Construct a sparse matrix of zeros.

    Parameters
    ----------
    x
        Sparse matrix to take the shape.

    Returns
    -------
    A sparse matrix
        The same as `x` with zero entries for all element.

    """

    # TODO: don't restrict to CSM formats
    _, _, indptr, shape = csm_properties(x)
    return CSM(format=x.format)(data=numpy.array([], dtype=x.type.dtype),
                                indices=numpy.array([], dtype='int32'),
                                indptr=tensor.zeros_like(indptr),
                                shape=shape) 

def sp_ones_like(x):
    """
    Construct a sparse matrix of ones with the same sparsity pattern.

    Parameters
    ----------
    x
        Sparse matrix to take the sparsity pattern.

    Returns
    -------
    A sparse matrix
        The same as `x` with data changed for ones.

    """
    # TODO: don't restrict to CSM formats
    data, indices, indptr, shape = csm_properties(x)
    return CSM(format=x.format)(tensor.ones_like(data), indices, indptr, shape) 

def perform(self, node, inp, outputs):
        (out,) = outputs
        x = inp[0]
        indices = inp[1]
        gz = inp[2]

        if x.format in ["csr"]:
            y = scipy.sparse.csr_matrix((x.shape[0], x.shape[1]))
        else:
            y = scipy.sparse.csc_matrix((x.shape[0], x.shape[1]))
        for a in range(0, len(indices)):
                y[indices[a]] = gz[a]

        out[0] = y 

def make_node(self, data, indices, indptr, shape):
        data = tensor.as_tensor_variable(data)

        if not isinstance(indices, gof.Variable):
            indices_ = numpy.asarray(indices)
            indices_32 = theano._asarray(indices, dtype='int32')
            assert (indices_ == indices_32).all()
            indices = indices_32
        if not isinstance(indptr, gof.Variable):
            indptr_ = numpy.asarray(indptr)
            indptr_32 = theano._asarray(indptr, dtype='int32')
            assert (indptr_ == indptr_32).all()
            indptr = indptr_32
        if not isinstance(shape, gof.Variable):
            shape_ = numpy.asarray(shape)
            shape_32 = theano._asarray(shape, dtype='int32')
            assert (shape_ == shape_32).all()
            shape = shape_32

        indices = tensor.as_tensor_variable(indices)
        indptr = tensor.as_tensor_variable(indptr)
        shape = tensor.as_tensor_variable(shape)

        if data.type.ndim != 1:
            raise TypeError('data argument must be a vector', data.type,
                            data.type.ndim)
        if indices.type.ndim != 1 or indices.type.dtype not in discrete_dtypes:
            raise TypeError('indices must be vector of integers', indices,
                            indices.type)
        if indptr.type.ndim != 1 or indptr.type.dtype not in discrete_dtypes:
            raise TypeError('indices must be vector of integers', indptr,
                            indptr.type)
        if shape.type.ndim != 1 or shape.type.dtype not in discrete_dtypes:
            raise TypeError('n_rows must be integer type', shape, shape.type)

        return gof.Apply(self,
                         [data, indices, indptr, shape],
                         [SparseType(dtype=data.type.dtype,
                                     format=self.format)()]) 

def perform(self, node, inputs, outputs):
        (x,) = inputs
        (z,) = outputs
        N, M = x.shape
        if N != M:
            raise ValueError('Diag only apply on square matrix')
        z[0] = x.diagonal() 

def perform(self, node, inputs, outputs):
        (x, y) = inputs
        (out,) = outputs
        assert _is_sparse(x) and _is_sparse(y)
        assert x.shape == y.shape
        assert x.data.shape == y.data.shape
        out[0] = x.copy()
        out[0].data += y.data 

def perform(self, node, inputs, outputs):
        (x, y) = inputs
        (out,) = outputs
        assert _is_sparse(x) and _is_sparse(y)
        assert len(x.shape) == 2
        assert y.shape == x.shape
        # This calls the element-wise multiple
        # x * y calls dot...
        out[0] = x.multiply(y) 

def perform(self, node, inputs, outputs):
        (x, y) = inputs
        (out,) = outputs
        assert _is_sparse(x) and _is_sparse(y)
        assert x.shape == y.shape
        out[0] = x + y 

def perform(self, node, inputs, outputs):
        (x_data, x_indices, x_indptr, x_shape,
         g_data, g_indices, g_indptr, g_shape) = inputs
        (g_out,) = outputs
        if len(x_indptr) - 1 == x_shape[0]:
            sp_dim = x_shape[1]
        else:
            sp_dim = x_shape[0]

        g_row = numpy.zeros(sp_dim, dtype=g_data.dtype)
        gout_data = numpy.zeros(x_data.shape, dtype=node.outputs[0].dtype)

        for i in range(len(x_indptr) - 1):
            for j_ptr in range(g_indptr[i], g_indptr[i + 1]):
                g_row[g_indices[j_ptr]] += g_data[j_ptr]

            for j_ptr in range(x_indptr[i], x_indptr[i + 1]):
                gout_data[j_ptr] = g_row[x_indices[j_ptr]]

            for j_ptr in range(g_indptr[i], g_indptr[i + 1]):
                g_row[g_indices[j_ptr]] = 0

        if self.kmap is None:
            g_out[0] = gout_data
        else:
            grad = numpy.zeros_like(x_data)
            grad[self.kmap] = gout_data
            g_out[0] = grad 

def perform(self, node, inputs, outputs):
        # for efficiency, if remap does nothing, then do not apply it
        (data, indices, indptr, shape) = inputs
        (out,) = outputs
        if self.kmap is not None:
            data = data[self.kmap]

        if len(shape) != 2:
            raise ValueError('Shape should be an array of length 2')
        if (data.shape != indices.shape and numpy.size(data) !=
                numpy.size(self.kmap)):
            errmsg = ('Data (shape ' + repr(data.shape) +
                      ' must have the same number of elements ' +
                      'as indices (shape' + repr(indices.shape) +
                      ') or elements as kmap (' +
                      repr(numpy.size(self.kmap)) + ')')
            raise ValueError(errmsg)
        if self.format == 'csc':
            out[0] = scipy.sparse.csc_matrix((data, indices.copy(),
                                              indptr.copy()),
                                             numpy.asarray(shape), copy=False)
        else:
            assert self.format == 'csr'
            out[0] = scipy.sparse.csr_matrix((data, indices.copy(),
                                              indptr.copy()), shape.copy(),
                                             copy=False) 

def load_data(mu, sigma, classn):
    X_test = np.empty(shape=(0, 3, 32, 32));
    X_val = np.empty(shape=(0, 3, 32, 32));
    X_train = np.empty(shape=(0, 3, 32, 32));

    y_test = np.empty(shape=(0, classn));
    y_val = np.empty(shape=(0, classn));
    y_train = np.empty(shape=(0, classn));

    lines = [line.rstrip('\n') for line in open('./data/image/label.txt')];
    linen = 0;
    for line in lines:
        linen += 1;
        img = line.split('\t')[0];
        lab = [int(x) for x in line.split('\t')[1].split()];
        png = misc.imread('./data/' + img).transpose()[0 : 3, 9 : 41, 9 : 41];
        png = np.expand_dims(png, axis=0).astype(np.float32) / 255;
        if linen % 100 <= 19:
            X_test = np.concatenate((X_test, png));
            y_test = np.concatenate((y_test, np.expand_dims(np.array(lab), axis=0)));
        elif linen % 100 >= 20 and linen % 100 <= 24:
            X_val = np.concatenate((X_val, png));
            y_val = np.concatenate((y_val, np.expand_dims(np.array(lab), axis=0)));
        elif linen % 100 >= 25:
            X_train = np.concatenate((X_train, png));
            y_train = np.concatenate((y_train, np.expand_dims(np.array(lab), axis=0)));

    X_train = X_train.astype(np.float32);
    X_val = X_val.astype(np.float32);
    X_test = X_test.astype(np.float32);
    y_train = y_train.astype(np.uint8);
    y_val = y_val.astype(np.uint8);
    y_test = y_test.astype(np.uint8);

    X_train = (X_train - mu) / sigma;
    X_val = (X_val - mu) / sigma;
    X_test = (X_test - mu) / sigma;

    print "Data Loaded", X_train.shape, y_train.shape, X_val.shape, y_val.shape, X_test.shape, y_test.shape;
    sys.stdout.flush();
    return X_train, y_train, X_val, y_val, X_test, y_test; 

def perform(self, node, inputs, outputs):
        (x, s) = inputs
        (z,) = outputs
        M, N = x.shape
        assert x.format == 'csc'
        assert s.shape == (N, )

        y = x.copy()

        for j in xrange(0, N):
            y.data[y.indptr[j]: y.indptr[j + 1]] *= s[j]

        z[0] = y 

def perform(self, node, inputs, outputs):
        (x, y) = inputs
        (out,) = outputs
        assert _is_sparse(x) and not _is_sparse(y)
        assert x.shape[1] == y.shape[0]
        out[0] = x.__class__(x.toarray() * y) 

def perform(self, node, inputs, outputs):
        (x, y) = inputs
        (out,) = outputs
        assert _is_sparse(x) and _is_sparse(y)
        assert x.shape == y.shape
        out[0] = self.comparison(x, y).astype('uint8')