Closed alanMachineLeraning closed 5 years ago
Hello alanMachineLeraning,
It seems that PyTorch had troubles computing the SVD (which is used as a cheap workaround to calculate the pseudo-inverse). Could you provide in_activations.size()
? Also, could you try changing --n-activations
and/or the number of samples to draw in the function dynamic_sampling
(cf. utils/
)?
Thank you! Solved! @pierrestock
Thank you! Solved! @pierrestock
@alanMachineLeraning How did you solve the issue? I am also having the same issue.
File "/home/zhang/kill-the-bits/src/quantization/em.py", line 83, in step A_pinv = torch.pinverse(in_activations) RuntimeError: svd_cuda: the updating process of SBDSDC did not converge (error: 8) environment:cuda9.0 nvidia-smi:410.93 ubuntu16.04