loss.py 文件源码

def forward(self, input1, input2, y):
        self.w1 = input1.new()
        self.w22 = input1.new()
        self.w = input1.new()
        self.w32 = input1.new()
        self._outputs = input1.new()

        _idx = input1.new().byte()

        buffer = torch.mul(input1, input2)
        torch.sum(buffer, 1, out=self.w1, keepdim=True)

        epsilon = 1e-12
        torch.mul(input1, input1, out=buffer)
        torch.sum(buffer, 1, out=self.w22, keepdim=True).add_(epsilon)

        self._outputs.resize_as_(self.w22).fill_(1)
        torch.div(self._outputs, self.w22, out=self.w22)
        self.w.resize_as_(self.w22).copy_(self.w22)

        torch.mul(input2, input2, out=buffer)
        torch.sum(buffer, 1, out=self.w32, keepdim=True).add_(epsilon)
        torch.div(self._outputs, self.w32, out=self.w32)
        self.w.mul_(self.w32)
        self.w.sqrt_()

        torch.mul(self.w1, self.w, out=self._outputs)
        self._outputs = self._outputs.select(1, 0)

        torch.eq(y, -1, out=_idx)
        self._outputs[_idx] = self._outputs[_idx].add_(-self.margin).clamp_(min=0)
        torch.eq(y, 1, out=_idx)
        self._outputs[_idx] = self._outputs[_idx].mul_(-1).add_(1)

        output = self._outputs.sum()

        if self.size_average:
            output = output / y.size(0)

        self.save_for_backward(input1, input2, y)
        return input1.new((output,))