Linus Härenstam-Nielsen
Linus Härenstam-Nielsen
I think I found the issue. I'm using a venv but I had ipympl-0.8.0 installed on my system level python3. So the following fixed it for me: ``` deactivate python3...
as a temporary fix to view the render you can replace lines 41-43 with something like the following: ``` root = jnp.array([-3, 0, 0]) look, up, left = jnp.eye(3) fov_deg...
@sfm-user-1 did you manage to solve the issue? I'm having the same problem on ubuntu, tried the master branch and all the pypi versions. Calling `poselib.CameraPose()` segfaults as well
@pablospe thanks for the link! With docker I can run the example without problems In fact, by looking at the Dockerfile I found that running ```bash pip install pybind11 scripts/build_python_package.sh...
@BowMonk I am using `-DCMAKE_CUDA_ARCHITECTURES=86`. See https://github.com/colmap/colmap/issues/1805 for more info
For me it's not working either with or without experimental config on `2.3.0+cu118`
hi, I'm having the same issue. Had to clone the repo and manually make the change to requirements.txt in order to pip install (the version on PyPi doesn't work with...
I never ended up solving this (had to move on to other things) will make sure to post if I figure it out though
@brentyi I see, thank you for the explanation! That's unfortunate but I'll try to reduce it to just one subcommand somehow for now then
Hi, I am facing similar issues. Here is what I got training the probes on `dino_b16`, `dinov2_b14` and `dinov2_l14` all with `dataset=navi_reldepth` dino_b16: ``` 2024-04-19 19:38:14.764 | INFO | __main__:train_model:290...