tba
Project description
DLC2Action is an action segmentation package that makes running and tracking of machine learning experiments easy.
Installation
From Github:
You can install DLC2Action for development by running this in your terminal.
git clone https://github.com/AlexEMG/DLC2Action
cd DLC2Action
conda create --name DLC2Action python=3.9
conda activate DLC2Action
python -m pip install .
Features
The functionality of DLC2Action includes:
- compiling and updating project-specific configuration files,
- filling in configuration dictionaries automatically whenever possible,
- saving training parameters and results,
- running predictions and hyperparameter searches,
- creating active learning files,
- loading hyperparameter search results in experiments and dumping them into configuration files,
- comparing new experiment parameters with the project history and loading pre-computed features (to save time) and previously created splits (to enforce consistency) when there is a match,
- filtering and displaying training, prediction and hyperparameter search history,
- plotting training curve comparisons
and more.
A quick example
You can start a new project, run an experiment, visualize it and use the trained model to make a prediction in a few lines of code.
from dlc2action.project import Project
# create a new project
project = Project('project_name', data_type='data_type', annotation_type='annotation_type',
data_path='path/to/data/folder', annotation_path='path/to/annotation/folder')
# set important parameters, like the set labels you want to predict
project.update_parameters(...)
# run a training episode
project.run_episode('episode_1')
# plot the results
project.plot_episodes(['episode_1'], metrics=['recall'])
# use the model trained in episode_1 to make a prediction for new data
project.run_prediction('prediction_1', episode_names=['episode_1'], data_path='path/to/new_data/folder')
How to get more information?
Check out the examples or read the documentation for a taste of what else you can do.
Note: For now you'll need to download the repo to look at the docs. They will look like this:
Acknowledgments
Liza Kozlova from the A. Mathis Group at EPFL is the main developer of DLC2Action.
We are grateful to many people for feedback, alpha-testing and suggestions, in particular to Andy Bonnetto, Lucas Stoffl, Margaret Lane, Marouane Jaakik, Steffen Schneider and Mackenzie Mathis.
License:
Note that the software is provided "as is", without warranty of any kind, express or implied. If you use the code or data, please cite us!
Reference:
Stay tuned for our first publication -- Any feedback on this beta release is welcome at this time. Thanks for using DLC2Action.
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
Built Distribution
Hashes for dlc2action-0.2b1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | f6953e823bfd0be893bb82002bd3475a3813306de05bd5fec967cc1def103be1 |
|
MD5 | 2337a2b8e4ede8a8353f7dbd2af48ff8 |
|
BLAKE2b-256 | 22470b564e6cd3cfa6671fa8428fd7dab4573a541963f58d577c18d3c1c47a64 |