domainbed/algorithms.py [312:326]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        self.register_buffer('update_count', torch.tensor([0]))

    @staticmethod
    def _irm_penalty(logits, y):
        device = "cuda" if logits[0][0].is_cuda else "cpu"
        scale = torch.tensor(1.).to(device).requires_grad_()
        loss_1 = F.cross_entropy(logits[::2] * scale, y[::2])
        loss_2 = F.cross_entropy(logits[1::2] * scale, y[1::2])
        grad_1 = autograd.grad(loss_1, [scale], create_graph=True)[0]
        grad_2 = autograd.grad(loss_2, [scale], create_graph=True)[0]
        result = torch.sum(grad_1 * grad_2)
        return result

    def update(self, minibatches, unlabeled=None):
        device = "cuda" if minibatches[0][0].is_cuda else "cpu"
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



domainbed/algorithms.py [1553:1567]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        self.register_buffer('update_count', torch.tensor([0]))

    @staticmethod
    def _irm_penalty(logits, y):
        device = "cuda" if logits[0][0].is_cuda else "cpu"
        scale = torch.tensor(1.).to(device).requires_grad_()
        loss_1 = F.cross_entropy(logits[::2] * scale, y[::2])
        loss_2 = F.cross_entropy(logits[1::2] * scale, y[1::2])
        grad_1 = autograd.grad(loss_1, [scale], create_graph=True)[0]
        grad_2 = autograd.grad(loss_2, [scale], create_graph=True)[0]
        result = torch.sum(grad_1 * grad_2)
        return result

    def update(self, minibatches, unlabeled=None):
        device = "cuda" if minibatches[0][0].is_cuda else "cpu"
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -