4a486c33d7faa7938355658abca7e936022389b0,robosat/tools/train.py,,train,#Any#Any#Any#Any#Any#Any#,120

Before Change

        for mask, output in zip(masks, outputs):
            prediction = output.detach()
            iou.add(mask.float(), prediction.max(0)[1].float())

    assert num_samples > 0, "dataset contains training images and labels"

After Change

        for mask, output in zip(masks, outputs):
            prediction = output.detach()
            metrics.add(mask, prediction)

    assert num_samples > 0, "dataset contains training images and labels"

    return {"loss": running_loss / num_samples, "iou": metrics.get_iou(), "acc": metrics.get_acc()}

Instances