Skip to main content

Vis4D Python package for Visual 4D scene understanding

Project description

Vis4D

A framework for dynamic scene understanding.

Installation

We currently support Python 3.7, 3.8 and 3.9.

Minimal requirements

You can install the minimal package dependencies via vanilla python and pip:

python3 -m pip install -r requirements.txt \
    -f https://download.pytorch.org/whl/cpu/torch_stable.html

This command installs pytorch without CUDA. Please look up pytorch website for installation on your configurations and install pytorch first.

If you're using conda, run the following commands:

conda create --name vis4d python=3.8
conda activate vis4d
conda install pytorch torchvision torchaudio cudatoolkit=11.0 -c pytorch
pip install -r requirements.txt

More information about torch and pytorch-lightning installation

Full requirements

To install the full package dependencies, please refer to the python and conda scripts. Or install the following packages:

Please note that specific models will require some of these packages.

Package installation

To install vis4d package,

python3 setup.py install

Usage

Training

python3 -m vis4d.engine.trainer train --config <config_path> <maybe other arguments>

Testing

python3 -m vis4d.engine.trainer test --config <config_path> <maybe other arguments>

Prediction

python3 -m vis4d.engine.trainer predict --config <config_path> <maybe other arguments>

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

vis4d-0.0.tar.gz (117.2 kB view details)

Uploaded Source

Built Distribution

vis4d-0.0-py3-none-any.whl (165.9 kB view details)

Uploaded Python 3

File details

Details for the file vis4d-0.0.tar.gz.

File metadata

  • Download URL: vis4d-0.0.tar.gz
  • Upload date:
  • Size: 117.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.2 importlib_metadata/3.7.2 pkginfo/1.7.0 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.2 CPython/3.9.7

File hashes

Hashes for vis4d-0.0.tar.gz
Algorithm Hash digest
SHA256 7ffc04a157e4322f33387b93a68bd71db57e62d353d7780e52a21aa3dd5e740f
MD5 2c5624a32ef521965eebd58cc01a0406
BLAKE2b-256 a384e606d98cc00c4c3956b4dde7d2773100c25d1c32f54a6bb839d3180fecd4

See more details on using hashes here.

File details

Details for the file vis4d-0.0-py3-none-any.whl.

File metadata

  • Download URL: vis4d-0.0-py3-none-any.whl
  • Upload date:
  • Size: 165.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.2 importlib_metadata/3.7.2 pkginfo/1.7.0 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.2 CPython/3.9.7

File hashes

Hashes for vis4d-0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 ff22edddd5e2d6592973a34f6930a21c5372a60c516bbf5220401f98263a3a88
MD5 5ce07df5cca1cf6cea1143af7ea941af
BLAKE2b-256 952acc4f47a130dc918e3385e5546230ff54a5d1c8ac98cfde315800596e379d

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page