4
0
mirror of https://github.com/nerfstudio-project/nerfstudio.git synced 2026-11-11 02:24:38 +08:00
A collaboration friendly studio for NeRFs
Go to file
2022-05-04 17:47:58 -07:00
.github/workflows Update lint checks 2022-05-02 15:10:49 -07:00
.vscode Add basic NGP encoder 2022-05-02 13:27:30 -07:00
configs Add multiple color options 2022-05-04 15:47:54 -07:00
data/blender/lego_test using test images. including some local data. black on save. disabled warnings for pytest 2022-04-29 16:23:05 +00:00
environment resizing image 2022-04-22 18:19:39 +00:00
external removing goat references 2022-04-29 16:36:47 +00:00
mattport Add accumulation 2022-05-04 17:47:58 -07:00
notebooks Add encoder visualizations 2022-05-03 16:10:19 -07:00
scripts merging masters new config 2022-04-29 22:29:43 +00:00
tests Add accumulation 2022-05-04 17:47:58 -07:00
viewer
.gitignore update gitignore 2022-05-02 09:47:21 -07:00
.gitmodules removing goat references 2022-04-29 16:36:47 +00:00
pyproject.toml
README.md modularizing hydra config and setting defaults (#46) 2022-04-29 14:39:43 -07:00
setup.py

MattPort

Quickstart

Installation: Setup the environment

# Clone the repo
git clone --recurse-submodules git@github.com:ethanweber/mattport.git

# Create the python environment
conda create --name mattport python=3.8.13
conda activate mattport
pip install -r environment/requirements.txt

# Install mattport as a library
python setup.py develop

# Running the test cases
pytest tests

Getting the data

Download the original NeRF dataset and put it in the following format.

- data/
    - blender/
        - fern/
        - lego/

Training a model

# Run with the default config
python scripts/run_train.py
# Run with config changes
python scripts/run_train.py machine_config.num_gpus=1

Logging and profiling features

We provide many logging functionalities for timing and/or tracking losses during training. All of these loggers are configurable via configs/logging.yml

  1. Writer: Logs losses and generated images during training to a specified output stream. Specify the type of writer (Tensorboard, local directory, Weights and Biases), and how often to log in the config.

  2. StatsTracker: Computes select statistics and prints to the terminal for local debugging. Specify the kinds of statistics to be logged, how often to log, and the maximum history buffer size in the config.

  3. Profiler: Computes the average total time of execution for any function with the @profiler.time_function decorator. Prints out the full profile at the termination of training or the program.

Setting up Jupyter

python -m jupyter lab build
bash environments/run_jupyter.sh

Tooling

We use autoenv to make setting up the environment and environment variables easier. This will run the .envrc file upon entering the /path/to/mattport folder. It will also remove the set environment parameters upon leaving.

# Install direnv.
sudo apt install direnv

# Add the following line to the bottom of your ~/.bashrc file.
eval "$(direnv hook bash)"

# Populate your .envrc with commands you want to run. Then, run the following to allow updates.
cd /path/to/mattport
direnv allow .