EwertzJN

Hello all, I am very interested in this extension for colmap and would like to test it already on my own dataset. Could you maybe give me instructions on how...

First, thank you very much for the quick feedback. My images are indeed equipped with geodata via EXIF, so the first row of the database after feature extraction looked like...

I have now been able to calculate a result, but on a different data set. Could it be that the images I want to use are possibly of too poor...

I tried a little bit more and activated `use_enu_coords(...)` which initially leads to a more reasonable output. At least this is what this [log](https://github.com/colmap/colmap/files/8224558/log.txt) suggests. Unfortunately, however, the program always...

It didn't solve my problem, but regardless of that, could it be that it was forgotten [here](https://github.com/nv-nguyen/cnos/blob/d8dc719df87dbcb1886dca5ff44d90e83336b080/src/scripts/inference_custom.py#L121) to apply the RGB transformation to the `templates`? I noticed this in my...

Hi, I faced the exact same issue where training would crash with a `NaN` tensor and an `AssertionError` after many epochs. This seems to happen specifically when using Automatic Mixed...

Hi everyone, I've been following this thread and issue \#72 as I was facing the exact same random `NaN` -\> `AssertionError` crash halfway through training. Like others have suggested, issues...

Hi all, for those still facing this `NaN` -\> `AssertionError` when training with Automatic Mixed Precision (`--use-amp`), I believe I've identified the root cause and have a stable fix. The...

@csampat-a, that's interesting. Yes, I was able to run multiple full training runs also on a custom dataset with my suggested fix. Before, I ran into the exact same problem...

Hello, I was also getting a "Loss is nan" error that would randomly stop my training. I believe I have found a specific fix, especially for those of you using...