Hi, I used the dcca loss to train my dnn and got the following error message:
46 [D1, V1] = torch.symeig(SigmaHat11, eigenvectors=True)
47 [D2, V2] = torch.symeig(SigmaHat22, eigenvectors=True)
48 # assert torch.isnan(D1).sum().item() == 0
RuntimeError: symeig_cuda: The algorithm failed to converge because the input matrix is ill-conditioned or has too many repeated eigenvalues (error code: 1807).
Do you have some methods to fix it? my cuda version is 11.3.
Hi, I used the dcca loss to train my dnn and got the following error message:
46 [D1, V1] = torch.symeig(SigmaHat11, eigenvectors=True)
47 [D2, V2] = torch.symeig(SigmaHat22, eigenvectors=True)
48 # assert torch.isnan(D1).sum().item() == 0
RuntimeError: symeig_cuda: The algorithm failed to converge because the input matrix is ill-conditioned or has too many repeated eigenvalues (error code: 1807).
Do you have some methods to fix it? my cuda version is 11.3.