VisT Python Package for perception and motion understanding
Project description
VisT
A perception system of tracking and motion understanding.
Installation
We currently support Python 3.7, 3.8 and 3.9.
You can install the package dependency via vanilla python and pip:
python3 -m pip install -r requirements.txt \
-f https://download.pytorch.org/whl/cpu/torch_stable.html
python3 -m pip install 'git+git://github.com/facebookresearch/detectron2.git'
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 vist python=3.8
conda activate vist
pip install -r requirements.txt
conda install pytorch torchvision torchaudio cudatoolkit=11.0 -c pytorch
pip install 'git+https://github.com/facebookresearch/detectron2.git'
You can also use python and conda scripts on CPU machine installation.
More information about torch and detectron2 installation
To install vist
package,
python3 setup.py install
Usage
Training
python3 tools/launch.py train --config <config_path> <maybe other arguments>
Testing
python3 tools/launch.py test --config <config_path> <maybe other arguments>
Prediction
python3 tools/launch.py predict --config <config_path> <maybe other arguments>
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
vist-0.0.tar.gz
(72.5 kB
view hashes)
Built Distribution
vist-0.0-py3-none-any.whl
(104.6 kB
view hashes)