Python torch.mul方法代码示例

# 需要导入模块: import torch [as 别名]
# 或者: from torch import mul [as 别名]
def node_forward(self, inputs, child_c, child_h):
        child_h_sum = torch.sum(child_h, dim=0, keepdim=True)

        iou = self.ioux(inputs) + self.iouh(child_h_sum)
        i, o, u = torch.split(iou, iou.size(1) // 3, dim=1)
        i, o, u = F.sigmoid(i), F.sigmoid(o), F.tanh(u)

        f = F.sigmoid(
            self.fh(child_h) +
            self.fx(inputs).repeat(len(child_h), 1)
        )
        fc = torch.mul(f, child_c)

        c = torch.mul(i, u) + torch.sum(fc, dim=0, keepdim=True)
        h = torch.mul(o, F.tanh(c))
        return c, h 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import mul [as 别名]
def forward(self, input1):
        self.batchgrid3d = torch.zeros(torch.Size([input1.size(0)]) + self.grid3d.size())

        for i in range(input1.size(0)):
            self.batchgrid3d[i] = self.grid3d

        self.batchgrid3d = Variable(self.batchgrid3d)
        #print(self.batchgrid3d)

        x = torch.sum(torch.mul(self.batchgrid3d, input1[:,:,:,0:4]), 3)
        y = torch.sum(torch.mul(self.batchgrid3d, input1[:,:,:,4:8]), 3)
        z = torch.sum(torch.mul(self.batchgrid3d, input1[:,:,:,8:]), 3)
        #print(x)
        r = torch.sqrt(x**2 + y**2 + z**2) + 1e-5

        #print(r)
        theta = torch.acos(z/r)/(np.pi/2)  - 1
        #phi = torch.atan(y/x)
        phi = torch.atan(y/(x + 1e-5))  + np.pi * x.lt(0).type(torch.FloatTensor) * (y.ge(0).type(torch.FloatTensor) - y.lt(0).type(torch.FloatTensor))
        phi = phi/np.pi


        output = torch.cat([theta,phi], 3)

        return output 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import mul [as 别名]
def forward(self, inputs):
        if len(inputs.shape) != 3:
            raise ValueError(
                "Unexpected inputs dimensions %d, expect to be 3 dimensions" % (len(inputs.shape)))
        inputs = torch.split(inputs, 1, dim=1)
        if self.bilinear_type == "all":
            p = [torch.mul(self.bilinear(v_i), v_j)
                 for v_i, v_j in itertools.combinations(inputs, 2)]
        elif self.bilinear_type == "each":
            p = [torch.mul(self.bilinear[i](inputs[i]), inputs[j])
                 for i, j in itertools.combinations(range(len(inputs)), 2)]
        elif self.bilinear_type == "interaction":
            p = [torch.mul(bilinear(v[0]), v[1])
                 for v, bilinear in zip(itertools.combinations(inputs, 2), self.bilinear)]
        else:
            raise NotImplementedError
        return torch.cat(p, dim=1) 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import mul [as 别名]
def compute_L_inverse(self,X,Y):
        N = X.size()[0] # num of points (along dim 0)
        # construct matrix K
        Xmat = X.expand(N,N)
        Ymat = Y.expand(N,N)
        P_dist_squared = torch.pow(Xmat-Xmat.transpose(0,1),2)+torch.pow(Ymat-Ymat.transpose(0,1),2)
        P_dist_squared[P_dist_squared==0]=1 # make diagonal 1 to avoid NaN in log computation
        K = torch.mul(P_dist_squared,torch.log(P_dist_squared))
        if self.reg_factor != 0:
            K+=torch.eye(K.size(0),K.size(1))*self.reg_factor
        # construct matrix L
        O = torch.FloatTensor(N,1).fill_(1)
        Z = torch.FloatTensor(3,3).fill_(0)       
        P = torch.cat((O,X,Y),1)
        L = torch.cat((torch.cat((K,P),1),torch.cat((P.transpose(0,1),Z),1)),0)
        Li = torch.inverse(L)
        if self.use_cuda:
            Li = Li.cuda()
        return Li 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import mul [as 别名]
def generate(self, target_layer):
        fmaps = self._find(self.fmap_pool, target_layer)
        grads = self._find(self.grad_pool, target_layer)
        weights = F.adaptive_avg_pool2d(grads, 1)

        gcam = torch.mul(fmaps, weights).sum(dim=1, keepdim=True)
        gcam = F.relu(gcam)
        gcam = F.interpolate(
            gcam, self.image_shape, mode="bilinear", align_corners=False
        )

        B, C, H, W = gcam.shape
        gcam = gcam.view(B, -1)
        gcam -= gcam.min(dim=1, keepdim=True)[0]
        gcam /= gcam.max(dim=1, keepdim=True)[0]
        gcam = gcam.view(B, C, H, W)

        return gcam 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import mul [as 别名]
def forward(self, x, hc=None):

        if hc is None:
            hc = (self.init_hidden(x), self.init_hidden(x))
        h, c = hc

        gate_x = self.fc_xh(x)
        gate_h = self.fc_hh(h)

        x_i, x_f, x_c, x_o = gate_x.chunk(self.num_chunks, 1)
        h_i, h_f, h_c, h_o = gate_h.chunk(self.num_chunks, 1)

        inputgate = torch.sigmoid(x_i + h_i)
        forgetgate = torch.sigmoid(x_f + h_f)
        cellgate = torch.tanh(x_c + h_c)
        outputgate = torch.sigmoid(x_o + h_o)

        c_ = torch.mul(forgetgate, c) + torch.mul(inputgate, cellgate)

        h_ = torch.mul(outputgate, torch.tanh(c_))

        return h_, c_ 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import mul [as 别名]
def _private_mul(self, other, equation: str):
        """Abstractly Multiplies two tensors

        Args:
            self: an AdditiveSharingTensor
            other: another AdditiveSharingTensor
            equation: a string representation of the equation to be computed in einstein
                summation form
        """
        # check to see that operation is either mul or matmul
        assert equation == "mul" or equation == "matmul"
        cmd = getattr(torch, equation)

        assert isinstance(other, AdditiveSharingTensor)

        assert len(self.child) == len(other.child)

        if self.crypto_provider is None:
            raise AttributeError("For multiplication a crypto_provider must be passed.")

        shares = spdz.spdz_mul(cmd, self, other, self.crypto_provider, self.field, self.dtype)

        return shares 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import mul [as 别名]
def pow(self, power):
        """
        Compute integer power of a number by recursion using mul

        This uses the following trick:
         - Divide power by 2 and multiply base to itself (if the power is even)
         - Decrement power by 1 to make it even and then follow the first step
        """
        base = self

        result = 1
        while power > 0:
            # If power is odd
            if power % 2 == 1:
                result = result * base

            # Divide the power by 2
            power = power // 2
            # Multiply base to itself
            base = base * base

        return result 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import mul [as 别名]
def weighted_cross_entropy_loss(prediction, label, output_mask=False):
    criterion = torch.nn.CrossEntropyLoss(reduce=False)
    label = torch.squeeze(label.long(), dim=0)
    nch = prediction.shape[1]
    label[label >= nch] = 0
    cost = criterion(prediction, label)
    mask = (label != 0).float()
    num_positive = torch.sum(mask).float()
    num_negative = mask.numel() - num_positive
    mask[mask == 1] = num_negative / (num_positive + num_negative)
    mask[mask == 0] = num_positive / (num_positive + num_negative)
    cost = torch.mul(cost, mask)
    if output_mask:
        return torch.sum(cost), (label != 0)
    else:
        return torch.sum(cost) 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import mul [as 别名]
def compute_L_inverse(self,X,Y):
        N = X.size()[0] # num of points (along dim 0)
        # construct matrix K
        Xmat = X.expand(N,N)
        Ymat = Y.expand(N,N)
        P_dist_squared = torch.pow(Xmat-Xmat.transpose(0,1),2)+torch.pow(Ymat-Ymat.transpose(0,1),2)
        P_dist_squared[P_dist_squared==0]=1 # make diagonal 1 to avoid NaN in log computation
        K = torch.mul(P_dist_squared,torch.log(P_dist_squared))
        # construct matrix L
        O = torch.FloatTensor(N,1).fill_(1)
        Z = torch.FloatTensor(3,3).fill_(0)       
        P = torch.cat((O,X,Y),1)
        L = torch.cat((torch.cat((K,P),1),torch.cat((P.transpose(0,1),Z),1)),0)
        Li = torch.inverse(L)
        if self.use_cuda:
            Li = Li.cuda()
        return Li 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import mul [as 别名]
def build_bow_rep(self, lat_code, n_sample):
        batch_sz = lat_code.size()[0]
        tup = self.estimate_param(latent_code=lat_code)
        mean = tup['mean']
        logvar = tup['logvar']

        kld = self.compute_KLD(tup)
        if n_sample == 1:
            eps = self.sample_cell(batch_size=batch_sz)
            vec = torch.mul(torch.exp(logvar), eps) + mean
            return tup, kld, vec

        vecs = []
        for ns in range(n_sample):
            eps = self.sample_cell(batch_size=batch_sz)
            vec = torch.mul(torch.exp(logvar), eps) + mean
            vecs.append(vec)
        vecs = torch.cat(vecs, dim=0)
        return tup, kld, vecs 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import mul [as 别名]
def forward(self, lvec, rvec):
        mult_dist = torch.mul(lvec, rvec)
        abs_dist = torch.abs(torch.add(lvec, -rvec))
        vec_dist = torch.cat((mult_dist, abs_dist), 1)

        out = F.sigmoid(self.wh(vec_dist))
        out = F.log_softmax(self.wp(out), dim=1)
        return out


# putting the whole model together 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import mul [as 别名]
def _signed_sqrt(self, x):
         x = torch.mul(x.sign(), torch.sqrt(x.abs()+self.thresh))
         return x 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import mul [as 别名]
def forward(self, x):
         bsn = 1
         batchSize, dim, h, w = x.data.shape
         x_flat = x.permute(0, 2, 3, 1).contiguous().view(-1, dim)  # batchsize,h, w, dim,
         y = torch.ones(batchSize, self.output_dim, device=x.device)

         for img in range(batchSize // bsn):
             segLen = bsn * h * w
             upper = batchSize * h * w
             interLarge = torch.arange(img * segLen, min(upper, (img + 1) * segLen), dtype=torch.long)
             interSmall = torch.arange(img * bsn, min(upper, (img + 1) * bsn), dtype=torch.long)
             batch_x = x_flat[interLarge, :]

             sketch1 = batch_x.mm(self.sparseM[0].to(x.device)).unsqueeze(2)
             sketch1 = torch.fft(torch.cat((sketch1, torch.zeros(sketch1.size(), device=x.device)), dim=2), 1)

             sketch2 = batch_x.mm(self.sparseM[1].to(x.device)).unsqueeze(2)
             sketch2 = torch.fft(torch.cat((sketch2, torch.zeros(sketch2.size(), device=x.device)), dim=2), 1)

             Re = sketch1[:, :, 0].mul(sketch2[:, :, 0]) - sketch1[:, :, 1].mul(sketch2[:, :, 1])
             Im = sketch1[:, :, 0].mul(sketch2[:, :, 1]) + sketch1[:, :, 1].mul(sketch2[:, :, 0])

             tmp_y = torch.ifft(torch.cat((Re.unsqueeze(2), Im.unsqueeze(2)), dim=2), 1)[:, :, 0]

             y[interSmall, :] = tmp_y.view(torch.numel(interSmall), h, w, self.output_dim).sum(dim=1).sum(dim=1)

         y = self._signed_sqrt(y)
         y = self._l2norm(y)
         return y 

# 需要导入模块: import torch [as 别名]
# 或者: from torch import mul [as 别名]
def forward(self, x, lengths=None):
        # x(batch, sentence, embed_dim)
        score = self.non_linear(self.fc(x))

        score = F.softmax(score, dim=-1)
        weights = torch.mul(x, score.unsqueeze(-1).expand_as(x))