janusch
janusch
I am cool with either colmap or another solutions as long as the quality does not suffer and it is reasonable easy to use. We can take the more convenient...
Seems not to train at all as at appears from your terminal output. Just loads the data. Not sure, what the issue is.
Hi @hugoycj, are you already working on this project?
No, it is not. I had no time to implement this fully. :(
Here is more input: https://twitter.com/janusch_patas/status/1696236337593016480 Saved to revisit later!
Seems irrelevant and nobody worked on it. Closed!
That sounds like a great plan. Having the software run in the cloud appears highly beneficial to me. Incorporating a Docker file isn't a massive addition, but it can deliver...
I think this can be closed after one year :)
No. I would suggest with own matmul and I believe quaternion ops. Its not much. The goal is to reduce deps from other libs to make it as self contained...
Same for glm. There might be overlapping operations with eigen that are used.