CUDA error on getting landmarks

[sidnetopia]

Hello, I'm getting an error on getting facial landmarks

---

RuntimeError Traceback (most recent call last) ~\AppData\Local\Temp/ipykernel_21192/3125532886.py in ----> 1 get_facial_landmarks(sample_img, fa)

~\AppData\Local\Temp/ipykernel_21192/3797573127.py in get_facial_landmarks(image, fa) 4 returns 128 feature vector. 0 to 500 5 ''' ----> 6 preds = fa.get_landmarks(image) 7 8 return preds

~.conda\envs\sort-cv\lib\site-packages\face_alignment\api.py in get_landmarks(self, image_or_path, detected_faces, return_bboxes) 107 return_bboxes {boolean} -- If True, return the face bounding boxes in addition to the keypoints. 108 """ --> 109 return self.get_landmarks_from_image(image_or_path, detected_faces, return_bboxes) 110 111 @torch.no_grad()

~.conda\envs\sort-cv\lib\site-packages\torch\autograd\grad_mode.py in decorate_context(*args, **kwargs) 26 def decorate_context(*args, **kwargs): 27 with self.class(): ---> 28 return func(*args, **kwargs) 29 return cast(F, decorate_context) 30

~.conda\envs\sort-cv\lib\site-packages\face_alignment\api.py in get_landmarks_from_image(self, image_or_path, detected_faces, return_bboxes) 166 167 heatmaps = heatmaps.to(self.device) --> 168 depth_pred = self.depth_prediciton_net( 169 torch.cat((inp, heatmaps), 1)).data.cpu().view(68, 1) 170 pts_img = torch.cat(

~.conda\envs\sort-cv\lib\site-packages\torch\nn\modules\module.py in _call_impl(self, *input, **kwargs) 1100 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks 1101 or _global_forward_hooks or _global_forward_pre_hooks): -> 1102 return forward_call(*input, **kwargs) 1103 # Do not call functions when jit is used 1104 full_backward_hooks, non_full_backward_hooks = [], []

RuntimeError: The following operation failed in the TorchScript interpreter. Traceback of TorchScript (most recent call last): File "", line 3, in forward

  def addmm(self: Tensor, mat1: Tensor, mat2: Tensor, beta: number = 1.0, alpha: number = 1.0):
      return self + mat1.mm(mat2)
                    ~~~~~~~ <--- HERE

  def batch_norm(input : Tensor, running_mean : Optional[Tensor], running_var : Optional[Tensor], training : bool, momentum : float, eps : float) -> Tensor:

RuntimeError: CUDA error: CUBLAS_STATUS_ALLOC_FAILED when calling cublasCreate(handle)

Face alignment version: 1.3.4 Python: 3.8.12