Dependencies

deepCINAC has the following minimum requirements, which must be installed before you can get started using PyNWB.

  1. Python 3.6, or 3.7

  2. pip

deepCINAC has been tested on Ubuntu 18.04.1 LTS, Windows 10 and macOS Mojave, using Python 3.6

Installation

Install release from PyPI

The Python Package Index (PyPI) is a repository of software for the Python programming language.

To install or update deepCINAC distribution from PyPI simply run:

$ pip install deepcinac

This will not automatically install the required dependencies. You can download our requirements.txt file and run :

$ pip -r requirements.txt

The following packages will be installed :

  • numpy

  • scanimage-tiff-reader

  • tifffile

  • keras

  • matplotlib

  • Pillow

  • scipy

  • networkx

  • seaborn

  • alt_model_checkpoint

  • hdf5storage

  • PyYAML

  • h5py

  • read-roi

Make sure your setuptools package is up to date, you might otherwise get this error message during installation: “ImportError: cannot import name ‘find_namespace_packages’ from ‘setuptools”

Two other packages will still be missing:

  • shapely

On Linux or MacOs simply run:

$ pip install shapely

For windows users, follow the instruction there. If you went on the wheels option, here are the instruction to install the wheel file: first open a console then cd to where you’ve downloaded your file and use:

$ pip install Shapely‑1.6.4.post2‑cp37‑cp37m‑win_amd64.whl

  • tensorflow

If you wish to use the GPU to increase the significantly the speed of prediction, then install tensorflow-gpu instead. For using the GPU, you will also need to install the NVIDIA CUDA Toolkit and Driver.

Here is a link to guide you to install it on windows (for french speakers).

For linux users, those links might be useful: nvidia website and a blog post.

Use the notebook with google colab to infer neuronal activity

If you just want to infer neuronal activity of your calcium imaging data and you don’t possess a GPU or don’t want to go through the process of configuring your environment to make use of it, you can run this notebook using google colab.

Google provides free virtual machines for you to use: with about 12GB RAM and 50GB hard drive space, and TensorFlow is pre-installed.

You will need a google account. Upload the notebook on google colab, then just follow the instructions in the notebook to go through.