Python torch.norm方法代码示例

# 需要导入模块: import torch [as 别名]
# 或者: from torch import norm [as 别名]
def complex_norm(
        complex_tensor: Tensor,
        power: float = 1.0
) -> Tensor:
    r"""Compute the norm of complex tensor input.

    Args:
        complex_tensor (Tensor): Tensor shape of `(..., complex=2)`
        power (float): Power of the norm. (Default: `1.0`).

    Returns:
        Tensor: Power of the normed input tensor. Shape of `(..., )`
    """

    # Replace by torch.norm once issue is fixed
    # https://github.com/pytorch/pytorch/issues/34279
    return complex_tensor.pow(2.).sum(-1).pow(0.5 * power) 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import norm [as 别名]
def magphase(
        complex_tensor: Tensor,
        power: float = 1.0
) -> Tuple[Tensor, Tensor]:
    r"""Separate a complex-valued spectrogram with shape `(..., 2)` into its magnitude and phase.

    Args:
        complex_tensor (Tensor): Tensor shape of `(..., complex=2)`
        power (float): Power of the norm. (Default: `1.0`)

    Returns:
        (Tensor, Tensor): The magnitude and phase of the complex tensor
    """
    mag = complex_norm(complex_tensor, power)
    phase = angle(complex_tensor)
    return mag, phase 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import norm [as 别名]
def AccelerationMatchingError(input, target):
	global lossfunc
	"""
	Takes input as (N,C,D,3) 3D coordinates and similiar targets (Here C is number of channels equivalent to number of joints)
	"""
	assert input.shape == target.shape
	assert len(input.shape) == 4
	#print('\n')
	#print(input[0,:8,0,:])
	#print(target[0,:8,0,:])
	input = input.cuda()
	inputdistances = input[:,:,1:,:] - input[:,:,:-1,:]
	inputdistances = torch.norm(inputdistances, dim=3)
	inputaccn = inputdistances[:,:,2:] + inputdistances[:,:,:-2] - 2*inputdistances[:,:,1:-1]
	targetdistances = target[:,:,1:,:] - target[:,:,:-1,:]
	targetdistances = torch.norm(targetdistances, dim=3)
	targetaccn = targetdistances[:,:,2:] + targetdistances[:,:,:-2] - 2*targetdistances[:,:,1:-1]
	return lossfunc(inputaccn, targetaccn) 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import norm [as 别名]
def poincare_case():
    torch.manual_seed(42)
    shape = manifold_shapes[geoopt.manifolds.PoincareBall]
    ex = torch.randn(*shape, dtype=torch.float64) / 3
    ev = torch.randn(*shape, dtype=torch.float64) / 3
    x = torch.tanh(torch.norm(ex)) * ex / torch.norm(ex)
    ex = x.clone()
    v = ev.clone()
    manifold = geoopt.PoincareBall().to(dtype=torch.float64)
    x = geoopt.ManifoldTensor(x, manifold=manifold)
    case = UnaryCase(shape, x, ex, v, ev, manifold)
    yield case
    manifold = geoopt.PoincareBallExact().to(dtype=torch.float64)
    x = geoopt.ManifoldTensor(x, manifold=manifold)
    case = UnaryCase(shape, x, ex, v, ev, manifold)
    yield case 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import norm [as 别名]
def sphere_subspace_case():
    torch.manual_seed(42)
    shape = manifold_shapes[geoopt.manifolds.Sphere]
    subspace = torch.rand(shape[-1], 2, dtype=torch.float64)

    Q, _ = geoopt.linalg.batch_linalg.qr(subspace)
    P = Q @ Q.t()

    ex = torch.randn(*shape, dtype=torch.float64)
    ev = torch.randn(*shape, dtype=torch.float64)
    x = (ex @ P.t()) / torch.norm(ex @ P.t())
    v = (ev - (x @ ev) * x) @ P.t()

    manifold = geoopt.Sphere(intersection=subspace)
    x = geoopt.ManifoldTensor(x, manifold=manifold)
    case = UnaryCase(shape, x, ex, v, ev, manifold)
    yield case
    manifold = geoopt.SphereExact(intersection=subspace)
    x = geoopt.ManifoldTensor(x, manifold=manifold)
    case = UnaryCase(shape, x, ex, v, ev, manifold)
    yield case 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import norm [as 别名]
def sphere_compliment_case():
    torch.manual_seed(42)
    shape = manifold_shapes[geoopt.manifolds.Sphere]
    complement = torch.rand(shape[-1], 1, dtype=torch.float64)

    Q, _ = geoopt.linalg.batch_linalg.qr(complement)
    P = -Q @ Q.transpose(-1, -2)
    P[..., torch.arange(P.shape[-2]), torch.arange(P.shape[-2])] += 1

    ex = torch.randn(*shape, dtype=torch.float64)
    ev = torch.randn(*shape, dtype=torch.float64)
    x = (ex @ P.t()) / torch.norm(ex @ P.t())
    v = (ev - (x @ ev) * x) @ P.t()

    manifold = geoopt.Sphere(complement=complement)
    x = geoopt.ManifoldTensor(x, manifold=manifold)
    case = UnaryCase(shape, x, ex, v, ev, manifold)
    yield case
    manifold = geoopt.SphereExact(complement=complement)
    x = geoopt.ManifoldTensor(x, manifold=manifold)
    case = UnaryCase(shape, x, ex, v, ev, manifold)
    yield case 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import norm [as 别名]
def sphere_case():
    torch.manual_seed(42)
    shape = manifold_shapes[geoopt.manifolds.Sphere]
    ex = torch.randn(*shape, dtype=torch.float64)
    ev = torch.randn(*shape, dtype=torch.float64)
    x = ex / torch.norm(ex)
    v = ev - (x @ ev) * x

    manifold = geoopt.Sphere()
    x = geoopt.ManifoldTensor(x, manifold=manifold)
    case = UnaryCase(shape, x, ex, v, ev, manifold)
    yield case
    manifold = geoopt.SphereExact()
    x = geoopt.ManifoldTensor(x, manifold=manifold)
    case = UnaryCase(shape, x, ex, v, ev, manifold)
    yield case 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import norm [as 别名]
def calculate_positive_embedding_loss(self, z, positive_edges):
        """
        Calculating the loss on the positive edge embedding distances
        :param z: Hidden vertex representation.
        :param positive_edges: Positive training edges.
        :return loss_term: Loss value on positive edge embedding.
        """
        self.positive_surrogates = [random.choice(self.nodes) for node in range(positive_edges.shape[1])]
        self.positive_surrogates = torch.from_numpy(np.array(self.positive_surrogates, dtype=np.int64).T)
        self.positive_surrogates = self.positive_surrogates.type(torch.long).to(self.device)
        positive_edges = torch.t(positive_edges)
        self.positive_z_i = z[positive_edges[:, 0], :]
        self.positive_z_j = z[positive_edges[:, 1], :]
        self.positive_z_k = z[self.positive_surrogates, :]
        norm_i_j = torch.norm(self.positive_z_i-self.positive_z_j, 2, 1, True).pow(2)
        norm_i_k = torch.norm(self.positive_z_i-self.positive_z_k, 2, 1, True).pow(2)
        term = norm_i_j-norm_i_k
        term[term < 0] = 0
        loss_term = term.mean()
        return loss_term 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import norm [as 别名]
def calculate_negative_embedding_loss(self, z, negative_edges):
        """
        Calculating the loss on the negative edge embedding distances
        :param z: Hidden vertex representation.
        :param negative_edges: Negative training edges.
        :return loss_term: Loss value on negative edge embedding.
        """
        self.negative_surrogates = [random.choice(self.nodes) for node in range(negative_edges.shape[1])]
        self.negative_surrogates = torch.from_numpy(np.array(self.negative_surrogates, dtype=np.int64).T)
        self.negative_surrogates = self.negative_surrogates.type(torch.long).to(self.device)
        negative_edges = torch.t(negative_edges)
        self.negative_z_i = z[negative_edges[:, 0], :]
        self.negative_z_j = z[negative_edges[:, 1], :]
        self.negative_z_k = z[self.negative_surrogates, :]
        norm_i_j = torch.norm(self.negative_z_i-self.negative_z_j, 2, 1, True).pow(2)
        norm_i_k = torch.norm(self.negative_z_i-self.negative_z_k, 2, 1, True).pow(2)
        term = norm_i_k-norm_i_j
        term[term < 0] = 0
        loss_term = term.mean()
        return loss_term 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import norm [as 别名]
def operator_norm_settings(domain, codomain):
    if domain == 1 and codomain == 1:
        # maximum l1-norm of column
        max_across_input_dims = True
        norm_type = 1
    elif domain == 1 and codomain == 2:
        # maximum l2-norm of column
        max_across_input_dims = True
        norm_type = 2
    elif domain == 1 and codomain == float("inf"):
        # maximum l-inf norm of column
        max_across_input_dims = True
        norm_type = float("inf")
    elif domain == 2 and codomain == float("inf"):
        # maximum l2-norm of row
        max_across_input_dims = False
        norm_type = 2
    elif domain == float("inf") and codomain == float("inf"):
        # maximum l1-norm of row
        max_across_input_dims = False
        norm_type = 1
    else:
        raise ValueError('Unknown combination of domain "{}" and codomain "{}"'.format(domain, codomain))

    return max_across_input_dims, norm_type 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import norm [as 别名]
def _power_iteration(self, A, num_simulations=30):
        # Ideally choose a random vector
        # To decrease the chance that our vector
        # Is orthogonal to the eigenvector
        b_k = torch.rand(A.shape[1]).unsqueeze(dim=1) * 0.5 - 1

        for _ in range(num_simulations):
            # calculate the matrix-by-vector product Ab
            b_k1 = torch.mm(A, b_k)

            # calculate the norm
            b_k1_norm = torch.norm(b_k1)

            # re normalize the vector
            b_k = b_k1 / b_k1_norm

        return b_k 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import norm [as 别名]
def __call__(self, data):
        (row, col), pos, pseudo = data.edge_index, data.pos, data.edge_attr
        assert pos.dim() == 2 and pos.size(1) == 2

        cart = pos[col] - pos[row]

        rho = torch.norm(cart, p=2, dim=-1).view(-1, 1)

        theta = torch.atan2(cart[..., 1], cart[..., 0]).view(-1, 1)
        theta = theta + (theta < 0).type_as(theta) * (2 * PI)

        if self.norm:
            rho = rho / (rho.max() if self.max is None else self.max)
            theta = theta / (2 * PI)

        polar = torch.cat([rho, theta], dim=-1)

        if pseudo is not None and self.cat:
            pseudo = pseudo.view(-1, 1) if pseudo.dim() == 1 else pseudo
            data.edge_attr = torch.cat([pseudo, polar.type_as(pos)], dim=-1)
        else:
            data.edge_attr = polar

        return data 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import norm [as 别名]
def loss_l2(self, l2=0):
        """L2 loss centered around mu_init, scaled optionally per-source.

        In other words, diagonal Tikhonov regularization,
            ||D(\mu-\mu_{init})||_2^2
        where D is diagonal.

        Args:
            - l2: A float or np.array representing the per-source regularization
                strengths to use
        """
        if isinstance(l2, (int, float)):
            D = l2 * torch.eye(self.d)
        else:
            D = torch.diag(torch.from_numpy(l2))

        # Note that mu is a matrix and this is the *Frobenius norm*
        return torch.norm(D @ (self.mu - self.mu_init)) ** 2 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import norm [as 别名]
def get_grad_norms(model, keys=[]):
    grads = {}
    for i, (k, param) in enumerate(dict(model.named_parameters()).items()):
        accept = False
        for key in keys:
            # match substring in collection of model keys
            if key in k:
                accept = True
                break
        if not accept:
            continue
        if param.grad is None:
            print('WARNING getting grads: {} param grad is None'.format(k))
            continue
        grads[k] = torch.norm(param.grad).cpu().item()
    return grads 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import norm [as 别名]
def __init__(self,
                 in_feats,
                 out_feats,
                 aggregator_type='mean',
                 feat_drop=0.,
                 bias=True,
                 norm=None,
                 activation=None,
                 G=None):
        super(AdaptSAGEConv, self).__init__()
        self._in_feats = in_feats
        self._out_feats = out_feats
        self.norm = norm
        self.feat_drop = nn.Dropout(feat_drop)
        self.activation = activation
        # self.fc_self = nn.Linear(in_feats, out_feats, bias=bias).double()
        self.fc_neigh = nn.Linear(in_feats, out_feats, bias=bias)
        self.reset_parameters()
        self.G = G