Function _extract_into_tensor

diff2flow/openai_diffusion/gaussian_diffusion.py:861–873

Extract values from a 1-D numpy array for a batch of indices. :param arr: the 1-D numpy array. :param timesteps: a tensor of indices into the array to extract. :param broadcast_shape: a larger shape of K dimensions with the batch dimension equal to the le

(arr, timesteps, broadcast_shape)

def _extract_into_tensor(arr, timesteps, broadcast_shape):
    """
    Extract values from a 1-D numpy array for a batch of indices.
    :param arr: the 1-D numpy array.
    :param timesteps: a tensor of indices into the array to extract.
    :param broadcast_shape: a larger shape of K dimensions with the batch
                            dimension equal to the length of timesteps.
    :return: a tensor of shape [batch_size, 1, ...] where the shape has K dims.
    """
    res = th.from_numpy(arr).to(device=timesteps.device)[timesteps].float()
    while len(res.shape) < len(broadcast_shape):
        res = res[..., None]
    return res + th.zeros(broadcast_shape, device=timesteps.device)