4.7 KiB
Installation
This repository is tested with CUDA 11.3. Make sure to install Conda before preceding.
Installing Conda
This step is fairly self-explanatory, but here are the basic steps. You can also find countless tutorials online.
cd /path/to/install/miniconda
mkdir -p miniconda3
wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O miniconda3/miniconda.sh
bash miniconda3/miniconda.sh -b -u -p miniconda3
rm -rf miniconda/miniconda.sh
Create the python environment
conda create --name nerfactory python=3.8.13
conda activate nerfactory
Clone the repo
git clone git@github.com:plenoptix/nerfactory.git
cd nerfactory
Install dependencies and nerfactory as a library
python -m pip install --upgrade pip
pip install -e .
Install tiny-cuda-nn (tcnn) to run instant_ngp
pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 -f https://download.pytorch.org/whl/torch_stable.html
pip install git+https://github.com/NVlabs/tiny-cuda-nn/#subdirectory=bindings/torch
Downloading data
Download the original NeRF Blender dataset. We support the major datasets and allow users to create their own dataset, described in detail here.
python scripts/downloads/download_data.py --dataset=blender
Use --help to view all currently available datasets. The resulting script should download and unpack the dataset as follows:
|─ nerfactory/
├─ data/
| ├─ blender/
| ├─ fern/
| ├─ lego/
...
|- <dataset_format>/
|- <scene>
...
Training a model
To run with all the defaults, e.g. vanilla nerf method with the blender lego image
Run a vanilla nerf model.
python scripts/run_train.py
Run a faster version with instant ngp using tcnn (without the viewer).
python scripts/run_train.py --config-name=graph_instant_ngp.yaml
Run with the viewer. However, you'll have to start the viewer server first. (See viewer docs)
python scripts/run_train.py --config-name=graph_instant_ngp.yaml viewer.enable=true
With support for Hydra, you can run with other configurations by changing appropriate configs defined in configs/ or by setting flags via command-line arguments.
Visualizing training runs
If you using a fast NeRF variant (ie. Instant-NGP), we reccomend using our viewer. See our viewer docs for more details. The viewer will allow interactive visualization of training in realtime.
Additionally, if you run everything with the default configuration, by default, we use TensorBoard to log all training curves, test images, and other stats. Once the job is launched, you will be able to track training by launching the tensorboard in outputs/blender_lego/vanilla_nerf/<timestamp>/<events.tfevents>.
tensorboard --logdir outputs
Rendering a Trajectory
To evaluate the trained NeRF, we provide an evaluation script that allows you to do benchmarking (see our benchmarking workflow) or to render out the scene with a custom trajectory and save the output to a video.
python scripts/run_eval.py render-trajectory --load-config=outputs/blender_lego/instant_ngp/2022-07-07_230905/config.yml --traj=spiral --output-path=output.mp4
Please note, this quickstart allows you to preform everything in a headless manner. We also provide a web-based visualizer that allows you to easily monitor training or render out trajectories. See our viewer docs for more.
FAQ
(tiny-cuda-error)=
TinyCUDA installation errors out with cuda mismatch
While installing tiny-cuda, you run into: The detected CUDA version mismatches the version that was used to compile PyTorch (10.2). Please make sure to use the same CUDA versions.
Solution:
pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 -f https://download.pytorch.org/whl/torch_stable.html
(pip-install-error)=
Installation errors, File "setup.py" not found
When installing dependencies and nerfactory with pip install -e ., you run into: ERROR: File "setup.py" not found. Directory cannot be installed in editable mode
Solution: This can be fixed by upgrading pip to the latest version:
python -m pip install --upgrade pip