Python torch.transpose方法代码示例

# 需要导入模块: import torch [as 别名]
# 或者: from torch import transpose [as 别名]
def m_ggnn(self, h_v, h_w, e_vw, opt={}):

        m = Variable(torch.zeros(h_w.size(0), h_w.size(1), self.args['out']).type_as(h_w.data))

        for w in range(h_w.size(1)):
            if torch.nonzero(e_vw[:, w, :].data).size():
                for i, el in enumerate(self.args['e_label']):
                    ind = (el == e_vw[:,w,:]).type_as(self.learn_args[0][i])

                    parameter_mat = self.learn_args[0][i][None, ...].expand(h_w.size(0), self.learn_args[0][i].size(0),
                                                                            self.learn_args[0][i].size(1))

                    m_w = torch.transpose(torch.bmm(torch.transpose(parameter_mat, 1, 2),
                                                                        torch.transpose(torch.unsqueeze(h_w[:, w, :], 1),
                                                                                        1, 2)), 1, 2)
                    m_w = torch.squeeze(m_w)
                    m[:,w,:] = ind.expand_as(m_w)*m_w
        return m 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import transpose [as 别名]
def r_duvenaud(self, h):
        # layers
        aux = []
        for l in range(len(h)):
            param_sz = self.learn_args[l].size()
            parameter_mat = torch.t(self.learn_args[l])[None, ...].expand(h[l].size(0), param_sz[1],
                                                                                      param_sz[0])

            aux.append(torch.transpose(torch.bmm(parameter_mat, torch.transpose(h[l], 1, 2)), 1, 2))

            for j in range(0, aux[l].size(1)):
                # Mask whole 0 vectors
                aux[l][:, j, :] = nn.Softmax()(aux[l][:, j, :].clone())*(torch.sum(aux[l][:, j, :] != 0, 1) > 0).expand_as(aux[l][:, j, :]).type_as(aux[l])

        aux = torch.sum(torch.sum(torch.stack(aux, 3), 3), 1)
        return self.learn_modules[0](torch.squeeze(aux)) 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import transpose [as 别名]
def max_pool1d(inputs, kernel_size, stride=1, padding='same'):
    '''
    inputs: [N, T, C]
    outputs: [N, T // stride, C]
    '''
    inputs = inputs.transpose(1, 2)  # [N, C, T]
    if padding == 'same':
        left = (kernel_size - 1) // 2
        right = (kernel_size - 1) - left
        pad = (left, right)
    else:
        pad = (0, 0)
    inputs = F.pad(inputs, pad)
    outputs = F.max_pool1d(inputs, kernel_size, stride)  # [N, C, T]
    outputs = outputs.transpose(1, 2)  # [N, T, C]

    return outputs 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import transpose [as 别名]
def cmmd(source, target, s_label, t_label, kernel_mul=2.0, kernel_num=5, fix_sigma=None):
    s_label = s_label.cpu()
    s_label = s_label.view(32,1)
    s_label = torch.zeros(32, 31).scatter_(1, s_label.data, 1)
    s_label = Variable(s_label).cuda()

    t_label = t_label.cpu()
    t_label = t_label.view(32, 1)
    t_label = torch.zeros(32, 31).scatter_(1, t_label.data, 1)
    t_label = Variable(t_label).cuda()

    batch_size = int(source.size()[0])
    kernels = guassian_kernel(source, target,
                              kernel_mul=kernel_mul, kernel_num=kernel_num, fix_sigma=fix_sigma)
    loss = 0
    XX = kernels[:batch_size, :batch_size]
    YY = kernels[batch_size:, batch_size:]
    XY = kernels[:batch_size, batch_size:]
    loss += torch.mean(torch.mm(s_label, torch.transpose(s_label, 0, 1)) * XX +
                      torch.mm(t_label, torch.transpose(t_label, 0, 1)) * YY -
                      2 * torch.mm(s_label, torch.transpose(t_label, 0, 1)) * XY)
    return loss 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import transpose [as 别名]
def forward(self, input_):
        """

        :param input_: sequences
        :return: outputs
        """
        batch_size = input_.size()[0]
        if self.time_dim == 2:
            input_ = input_.transpose(1, 2).contiguous()
        input_ = input_.view(-1, self.input_size)

        out = self.linear(input_).view(batch_size, -1, self.output_size)

        if self.time_dim == 2:
            out = out.contiguous().transpose(1, 2)

        return out 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import transpose [as 别名]
def intersection_area(yx_min1, yx_max1, yx_min2, yx_max2):
    """
    Calculates the intersection area of two lists of bounding boxes.
    :author 申瑞珉 (Ruimin Shen)
    :param yx_min1: The top left coordinates (y, x) of the first list (size [N1, 2]) of bounding boxes.
    :param yx_max1: The bottom right coordinates (y, x) of the first list (size [N1, 2]) of bounding boxes.
    :param yx_min2: The top left coordinates (y, x) of the second list (size [N2, 2]) of bounding boxes.
    :param yx_max2: The bottom right coordinates (y, x) of the second list (size [N2, 2]) of bounding boxes.
    :return: The matrix (size [N1, N2]) of the intersection area.
    """
    ymin1, xmin1 = torch.split(yx_min1, 1, -1)
    ymax1, xmax1 = torch.split(yx_max1, 1, -1)
    ymin2, xmin2 = torch.split(yx_min2, 1, -1)
    ymax2, xmax2 = torch.split(yx_max2, 1, -1)
    max_ymin = torch.max(ymin1.repeat(1, ymin2.size(0)), torch.transpose(ymin2, 0, 1).repeat(ymin1.size(0), 1)) # PyTorch's bug
    min_ymax = torch.min(ymax1.repeat(1, ymax2.size(0)), torch.transpose(ymax2, 0, 1).repeat(ymax1.size(0), 1)) # PyTorch's bug
    height = torch.clamp(min_ymax - max_ymin, min=0)
    max_xmin = torch.max(xmin1.repeat(1, xmin2.size(0)), torch.transpose(xmin2, 0, 1).repeat(xmin1.size(0), 1)) # PyTorch's bug
    min_xmax = torch.min(xmax1.repeat(1, xmax2.size(0)), torch.transpose(xmax2, 0, 1).repeat(xmax1.size(0), 1)) # PyTorch's bug
    width = torch.clamp(min_xmax - max_xmin, min=0)
    return height * width 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import transpose [as 别名]
def batch_intersection_area(yx_min1, yx_max1, yx_min2, yx_max2):
    """
    Calculates the intersection area of two lists of bounding boxes for N independent batches.
    :author 申瑞珉 (Ruimin Shen)
    :param yx_min1: The top left coordinates (y, x) of the first lists (size [N, N1, 2]) of bounding boxes.
    :param yx_max1: The bottom right coordinates (y, x) of the first lists (size [N, N1, 2]) of bounding boxes.
    :param yx_min2: The top left coordinates (y, x) of the second lists (size [N, N2, 2]) of bounding boxes.
    :param yx_max2: The bottom right coordinates (y, x) of the second lists (size [N, N2, 2]) of bounding boxes.
    :return: The matrics (size [N, N1, N2]) of the intersection area.
    """
    ymin1, xmin1 = torch.split(yx_min1, 1, -1)
    ymax1, xmax1 = torch.split(yx_max1, 1, -1)
    ymin2, xmin2 = torch.split(yx_min2, 1, -1)
    ymax2, xmax2 = torch.split(yx_max2, 1, -1)
    max_ymin = torch.max(ymin1.repeat(1, 1, ymin2.size(1)), torch.transpose(ymin2, 1, 2).repeat(1, ymin1.size(1), 1)) # PyTorch's bug
    min_ymax = torch.min(ymax1.repeat(1, 1, ymax2.size(1)), torch.transpose(ymax2, 1, 2).repeat(1, ymax1.size(1), 1)) # PyTorch's bug
    height = torch.clamp(min_ymax - max_ymin, min=0)
    max_xmin = torch.max(xmin1.repeat(1, 1, xmin2.size(1)), torch.transpose(xmin2, 1, 2).repeat(1, xmin1.size(1), 1)) # PyTorch's bug
    min_xmax = torch.min(xmax1.repeat(1, 1, xmax2.size(1)), torch.transpose(xmax2, 1, 2).repeat(1, xmax1.size(1), 1)) # PyTorch's bug
    width = torch.clamp(min_xmax - max_xmin, min=0)
    return height * width 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import transpose [as 别名]
def birkhoff_case():
    torch.manual_seed(42)
    shape = manifold_shapes[geoopt.manifolds.BirkhoffPolytope]
    ex = torch.randn(*shape, dtype=torch.float64).abs()
    ev = torch.randn(*shape, dtype=torch.float64)
    max_iter = 100
    eps = 1e-12
    tol = 1e-5
    iter = 0
    c = 1.0 / (torch.sum(ex, dim=-2, keepdim=True) + eps)
    r = 1.0 / (torch.matmul(ex, c.transpose(-1, -2)) + eps)
    while iter < max_iter:
        iter += 1
        cinv = torch.matmul(r.transpose(-1, -2), ex)
        if torch.max(torch.abs(cinv * c - 1)) <= tol:
            break
        c = 1.0 / (cinv + eps)
        r = 1.0 / ((ex @ c.transpose(-1, -2)) + eps)
    x = ex * (r @ c)

    v = proju_original(x, ev)
    manifold = geoopt.manifolds.BirkhoffPolytope()
    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 transpose [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 transpose [as 别名]
def channel_shuffle(x, groups):
    batchsize, num_channels, height, width = x.data.size()

    channels_per_group = num_channels // groups

    # reshape
    x = x.view(batchsize, groups,
               channels_per_group, height, width)

    # transpose
    # - contiguous() required if transpose() is used before view().
    #   See https://github.com/pytorch/pytorch/issues/764
    x = torch.transpose(x, 1, 2).contiguous()

    # flatten
    x = x.view(batchsize, -1, height, width)

    return x 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import transpose [as 别名]
def convolutional_layer(self, inputs):
        convolution_all = []
        conv_wts = []
        for i in range(self.seq_len):
            convolution_one_month = []
            for j in range(self.pad_size):
                convolution = self.conv(torch.unsqueeze(inputs[:, i, j], dim=1))
                convolution_one_month.append(convolution)
            convolution_one_month = torch.stack(convolution_one_month)
            convolution_one_month = torch.squeeze(convolution_one_month, dim=3)
            convolution_one_month = torch.transpose(convolution_one_month, 0, 1)
            convolution_one_month = torch.transpose(convolution_one_month, 1, 2)
            convolution_one_month = torch.squeeze(convolution_one_month, dim=1)
            convolution_one_month = self.func_tanh(convolution_one_month)
            convolution_one_month = torch.unsqueeze(convolution_one_month, dim=1)
            vec = torch.bmm(convolution_one_month, inputs[:, i])
            convolution_all.append(vec)
            conv_wts.append(convolution_one_month)
        convolution_all = torch.stack(convolution_all, dim=1)
        convolution_all = torch.squeeze(convolution_all, dim=2)
        conv_wts = torch.squeeze(torch.stack(conv_wts, dim=1), dim=2)
        return convolution_all, conv_wts 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import transpose [as 别名]
def get_loss(pred, y, criterion, mtr, a=0.5):
    """
    To calculate loss
    :param pred: predicted value
    :param y: actual value
    :param criterion: nn.CrossEntropyLoss
    :param mtr: beta matrix
    """
    mtr_t = torch.transpose(mtr, 1, 2)
    aa = torch.bmm(mtr, mtr_t)
    loss_fn = 0
    for i in range(aa.size()[0]):
        aai = torch.add(aa[i, ], Variable(torch.neg(torch.eye(mtr.size()[1]))))
        loss_fn += torch.trace(torch.mul(aai, aai).data)
    loss_fn /= aa.size()[0]
    loss = torch.add(criterion(pred, y), Variable(torch.FloatTensor([loss_fn * a])))
    return loss 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import transpose [as 别名]
def similarity(self, s1, l1, s2, l2):
        """
        :param s1: [B, t1, D]
        :param l1: [B]
        :param s2: [B, t2, D]
        :param l2: [B]
        :return:
        """
        batch_size = s1.size(0)
        t1 = s1.size(1)
        t2 = s2.size(1)
        S = torch.bmm(s1, s2.transpose(1,
                                       2))  # [B, t1, D] * [B, D, t2] -> [B, t1, t2] S is the similarity matrix from biDAF paper. [B, T1, T2]

        s_mask = S.data.new(*S.size()).fill_(1).byte()  # [B, T1, T2]
        # Init similarity mask using lengths
        for i, (l_1, l_2) in enumerate(zip(l1, l2)):
            s_mask[i][:l_1, :l_2] = 0

        s_mask = Variable(s_mask)
        S.data.masked_fill_(s_mask.data.byte(), -math.inf)
        return S 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import transpose [as 别名]
def __init__(self, n_classes, n_blocks, pyramids, class_emb):
        super(DeepLabV2, self).__init__()
        if class_emb is not None:
            self.emb_size = class_emb.shape[1]
            self.class_emb = torch.transpose(class_emb, 1, 0).float().cuda()
        self.add_module(
            "layer1",
            nn.Sequential(
                OrderedDict(
                    [
                        ("conv1", _ConvBatchNormReLU(3, 64, 7, 2, 3, 1)),
                        ("pool", nn.MaxPool2d(3, 2, 1, ceil_mode=True)),
                    ]
                )
            ),
        )
        self.add_module("layer2", _ResBlock(n_blocks[0], 64, 64, 256, 1, 1))
        self.add_module("layer3", _ResBlock(n_blocks[1], 256, 128, 512, 2, 1))
        self.add_module("layer4", _ResBlock(n_blocks[2], 512, 256, 1024, 1, 2))
        self.add_module("layer5", _ResBlock(n_blocks[3], 1024, 512, 2048, 1, 4))
        self.add_module("aspp", _ASPPModule(2048, n_classes, pyramids))

        print("DeepLab Outputs: {}".format(n_classes)) 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import transpose [as 别名]
def _dropping(self, delta):
        weight = self.conv.weight * self.mask
        ### Sum up all kernels
        ### Assume only apply to 1x1 conv to speed up
        assert weight.size()[-1] == 1
        weight = weight.abs().squeeze()
        assert weight.size()[0] == self.out_channels
        assert weight.size()[1] == self.in_channels
        d_out = self.out_channels // self.groups
        ### Shuffle weight
        weight = weight.view(d_out, self.groups, self.in_channels)
        weight = weight.transpose(0, 1).contiguous()
        weight = weight.view(self.out_channels, self.in_channels)
        ### Sort and drop
        for i in range(self.groups):
            wi = weight[i * d_out:(i + 1) * d_out, :]
            ### Take corresponding delta index
            di = wi.sum(0).sort()[1][self.count:self.count + delta]
            for d in di.data:
                self._mask[i::self.groups, d, :, :].fill_(0)
        self.count = self.count + delta