cov can direct finetune?

[zhouilu]

i try load ply and cov vq, then i direct finetune cov param, like

    def get_covariance(self, scaling_modifier=1, strip_sym: bool = True):
        if self.is_gaussian_indexed:
            return self._cov[self._gaussian_indices]
        else:
            return self._cov

but it will cause crash

 1.0 - ssim(image, gt_image)
  File "c3dgs/utils/loss_utils.py", line 38, in ssim
    window = window.cuda(img1.get_device())
RuntimeError: CUDA error: an illegal memory access was encountered
CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Training progress:   6%|█████████████████▏

Do you have any suggestions? thanks