Metadata-Version: 2.1
Name: vidtrain
Version: 0.1.2
Summary: Deep learning annotation training and prediction workflow for microscopy video data
Home-page: https://gitlab.com/Thawn/vidtrain
Author: Thawn
Author-email: webmaster@korten.at
License: UNKNOWN
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >3.7.0, <3.8.0
Description-Content-Type: text/markdown
Requires-Dist: tensorflow (<2)
Requires-Dist: keras (>=2)
Requires-Dist: scikit-learn (>=0.22)
Requires-Dist: numpy (>=1.18)
Requires-Dist: matplotlib (>=3.2)
Requires-Dist: pandas (>=1)
Requires-Dist: pandastable (>=0.12)
Requires-Dist: tifffile (>=2020.5)
Requires-Dist: micdata (>=0.1)
Provides-Extra: bioformats
Requires-Dist: python-bioformats (>=1.5) ; extra == 'bioformats'
Requires-Dist: javabridge (>=1.0.18) ; extra == 'bioformats'

# VidTrain

Train deep neural networks to analyze video data.

## Installation

1. [Install anaconda](https://docs.conda.io/projects/conda/en/latest/user-guide/install/index.html)
2. (Optional) Install a python-capable IDE like [Visual Studio Code](https://code.visualstudio.com/)
3. Open a command line terminal to install `vidtrain`: 
   1. Create a python 3.7 environment: `conda create --name vidtrain python=3.7`. Note, the python version must be exactly 3.7 [[1]](#Notes)
   2. Activate the environment `conda activate vidtrain`
   3. Install vidtrain `pip install vidtrain`



## Notes
[1]  The code uses some features that were introduced in 3.7 (dictionaries that are ordered by default), meaning it will not work properly with python <3.7. Furthermore, it uses Tensorflow 1 , which dpes not support 3.8. Thus, the python version must be *exactly* 3.7. In the future, it is planned to migrate to Tensorflow 2 and at that point, vidtrain will also work on python 3.8. However, this will require rewriting at least the data generator for the validation data.

