b3d repository

This repository contains code for Bayesian 3D inverse graphics.

The b3d/bayes3d/ subdirectory contains code for the bayes3d project, and the b3d/chisight/ subdirectory contains code for post-bayes3D ChiSight systems (currently, SAMA4D).

Installing b3d

Create b3d conda environment:

conda create -n b3d python=3.12

Run install script:

bash -i install.sh

Installing CUDA 12.3+

Run nvidia-smi

+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 550.54.15              Driver Version: 550.54.15      CUDA Version: 12.4     |
|-----------------------------------------+------------------------+----------------------+

and verify that CUDA Version: xx.x is >= 12.3.

If not, ensure your NVIDIA GPU supports CUDA 12.3+ and install a NVIDIA driver version compatible with 12.3+. For GCP instances, use:

sudo sh -c "echo 'export DRIVER_VERSION=550.54.15' > /opt/deeplearning/driver-version.sh"
/opt/deeplearning/install-driver.sh

If the above commands fail, then first uninstall the existing driver by running the below, then try again.

/opt/deeplearning/uninstall-driver.sh
sudo reboot

Environment Variables

Add the following to your bash_rc:

export XLA_PYTHON_CLIENT_PREALLOCATE="false"
export XLA_PYTHON_CLIENT_ALLOCATOR="platform"

Visualizer

Tunnel port 8812 for Rerun visualization by adding the RemoteForwardline to your ssh config:

Host xx.xx.xxx.xxx
    HostName xx.xx.xxx.xxx
    IdentityFile ~/.ssh/id_rsa
    User thomasbayes
    RemoteForward 8812 127.0.0.1:8812

Install rerun on local machine pip install rerun-sdk and open viewer:

rerun --port 8812