Ajay Kumar Patel

icon indicating a website link https://www.linkedin.com/in/ajay-kumar-patel-6989b5117/ icon indicating an email [email protected]

icon company CDAC icon location Mumbai icon location I like solving my problems in fastest manner and hence technology is never a barrier for me. Love - Python, Crush- JAVA, Savior - C .

Results 6 comments of Ajay Kumar Patel

untimeError: torch.linalg.cholesky: The factorization could not be completed because the input is not positive-definite (the leading minor of order 1 is not positive-definite)

> I have the same Issue. @sjg02122 I got this resolved by downgrading torch version to torch=1.7

untimeError: torch.linalg.cholesky: The factorization could not be completed because the input is not positive-definite (the leading minor of order 1 is not positive-definite)

> I cannot manage to reproduce this error on GPU with torch=1.10.0 and CUDA=10.2. Are you running this on CPU? Could you check if there is any NaN in the...

Using COLMAP to generate Cambridge landmark scene's poses from scratch

Thanks for quick response. I'm interested in evaluating with my own model and grouth truth.

Using COLMAP to generate Cambridge landmark scene's poses from scratch

I'm developing a generalized pipeline for my own data where I don't have pose information, only RGB images are there. So I'm testing that with Cambridge landmarks.

How to use colmap model_aligner? Please explain with example.

Yes, can you please explain how this works?

How to use colmap model_aligner? Please explain with example.

Thanks for the explanation @tsattler.