Anthony Zhang

I had this error, but I just fixed it by merging the main into my branch (I also installed nerfstudio with `pip install -e .`). I currently have gsplat==1.9.0 though

This is still an error - on line 14 inside the cell "Install Nerfstudio and Dependencies (~8 min)": `!gdown "https://drive.google.com/u/0/uc?id=15WngFRNar_b8CaPR5R-hvQ3eAnlyk_SL&confirm=t"` tinycudann is able to be installed perfectly, but the drive...

@jfenton888 thank you for the catch! I've updated the PR with this change

Hey thanks for the report, we have a bugfix in the making but the issue is with the colmap build - for now it can be fixed if you run...

Yes you're right, my mistake - I put the wrong link but I've updated it to be the branch which contains the fix - if you don't want to pull...

Perhaps you can try to run the command in the terminal command line interface (just copy and paste the command into the terminal given by the `ns-train` cell using the...

@kesitrifork @noureldinabdelalim @SaifeldeenAdel I was able to get it working with the `xterm` module. It took about 16 minutes to generate all the camera poses for 300 frames of a...

@noureldinabdelalim Did you try downloading the COLMAP binary from [this PR](https://github.com/nerfstudio-project/nerfstudio/blob/e159102681b3f2e82115ab135fc426923da12e61/colab/demo.ipynb)? You can just copy and paste the first cell there because it installs COLMAP with CUDA which can help...

This fix works! I'm able to render once `ffmpeg` version is 4.2.2 For others, if your conda environment is running `ffmpeg` version 4.3, simply reinstall with version 4.2.2 using the...

After experimenting more, there is a workaround without dealing with colab's python version - if you run `ns-train` on the colab terminal (requires colab pro), the model is able to...