0efc69bdc63b49673fd3df91341f91a84abd33ba,foolbox/models/pytorch.py,PyTorchModel,predictions_and_gradient,#PyTorchModel#Any#Any#,100

Before Change

        target = target.to(self.device)

        images = image[np.newaxis]
        images = torch.from_numpy(images)
        images = images.to(self.device)

        if self._old_pytorch():  // pragma: no cover
            target = Variable(target)
            images = Variable(images, requires_grad=True)
        else:
            images.requires_grad_()

        predictions = self._model(images)
        ce = nn.CrossEntropyLoss()
        loss = ce(predictions, target)
        loss.backward()
        grad = images.grad

        if self._old_pytorch():  // pragma: no cover
            predictions = predictions.data
        predictions = predictions.to(self.device)

        if not self._old_pytorch():
            predictions = predictions.detach()
        predictions = predictions.numpy()

After Change

        target = torch.from_numpy(target).to(self.device)

        images = image[np.newaxis]
        images = torch.from_numpy(images).to(self.device)

        if self._old_pytorch():  // pragma: no cover
            target = Variable(target)
            images = Variable(images, requires_grad=True)
        else:
            images.requires_grad_()

        predictions = self._model(images)
        ce = nn.CrossEntropyLoss()
        loss = ce(predictions, target)
        loss.backward()
        grad = images.grad

        if self._old_pytorch():  // pragma: no cover
            predictions = predictions.data
        if self.device != "cpu":
            predictions = predictions.to("cpu")

        if not self._old_pytorch():
            predictions = predictions.detach()
        predictions = predictions.numpy()
        predictions = np.squeeze(predictions, axis=0)

Instances