napari-debcr

DeBCR is a Python-based framework for light microscopy data enhancement, including denoising and deconvolution.

napari-debcr is add-on plugin, created to provide a graphical interface for DeBCR in Napari viewer.

This plugin was initialized with copier using the napari-plugin-template.

License

This is an open-source project and is licensed under MIT license.

Contact

For any questions or bur-reports related to:

• the napari-debcr plugin - use the napari-debcr GitHub Issue Tracker;
• the core debcr package - use the DeBCR GitHub Issue Tracker.

Installation

As for the core package debcr, there are two hardware-based installation options for napari-debcr:

• napari-debcr[tf-gpu] - for a GPU-based trainig and prediction (recommended);
• napari-debcr[tf-cpu] - for a CPU-only execution (note: training on CPUs might be quite slow!).

GPU prerequisites

For a GPU version you need:

• a GPU device with at least 12Gb of VRAM;
• a compatible CUDA Toolkit (recommemded: CUDA-11.7);
• a compatible cuDNN library (recommemded: v8.4.0 for CUDA-11.x from cuDNN archive).

For more info on GPU dependencies please check our GPU-advice page on DeBCR GitHub.

Create a package environment (optional)

For a clean isolated installation, we advice using one of Python package environment managers, for example:

• micromamba/mamba (see mamba.readthedocs.io)
• conda-forge (see conda-forge.org)

Create an environment for napari-debcr using

micromamba env create -n napari-debcr python=3.9 -y

and activate it for further installation or usage by

micromamba activate napari-debcr

Install napari

Make sure you have napari installed. To install it via pip use:

pip install napari[all]

Install napari-debcr

Install one of the napari-debcr versions:

• GPU (recommended; backend: TensorFlow-GPU-v2.11):

  pip install 'napari-debcr[tf-gpu]'
  

• CPU (limited; backend: TensorFlow-CPU-v2.11)

  pip install 'napari-debcr[tf-cpu]'
  

Test GPU visibility

For a GPU version installation, it is recommended to check if your GPU device is recognised by TensorFlow using

python -c "import tensorflow as tf; print(tf.config.list_physical_devices('GPU'))"

which for a single GPU device should produce a similar output as below:

[PhysicalDevice(name='/physical_device:GPU:0', device_type='GPU')]

If your GPU device list is empty, please check our GPU-advice page on DeBCR GitHub.

Usage

To start using napari-debcr,

1. activate napari-debcr environment, if was inactive, by

micromamba activate napari-debcr

2. start Napari by typing

napari

3. in Napari window, open napari-debcr plugin by clicking in the main menu

Plugins → DeBCR (DeBCR)