Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/cea-metrocarac/pca-n2v

https://github.com/cea-metrocarac/pca-n2v

Science Score: 36.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: zenodo.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (12.8%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: CEA-MetroCarac
  • Language: Jupyter Notebook
  • Default Branch: main
  • Size: 1.95 MB
Statistics
  • Stars: 1
  • Watchers: 2
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 1 year ago · Last pushed about 1 year ago
Metadata Files
Readme

README.md

PCA-n2v

This repository contains the implementation of PCA-n2v (Noise2Void), based on the package n2v.

Running the example notebook

This code should run on recent versions of Python, though the package n2v cannot be installed on 3.12+.

From a clean virtual or conda environment install the requirements:

bash pip install -r requirements.txt

If this fails due to missing git, install a copy of git from here. We must install n2v from GitHub in order to have certain bugfixes which are not yet released to PyPi.

If you have a CUDA-capable GPU then you can also run:

bash pip install -r "tensorflow[and-cuda]<2.16"

though it would be best to follow the n2v readme for configuring Tensorflow and CUDA appropriately.

From this folder launch the Jupyter notebook server:

jupyter notebook

then load the file Example_denoising.ipynb.

Example data

The example data for the repository are available at the following Zenodo page. We use the file Alga_raw.npz placed in the ./data directory.

Note on data import

Appropriate data import is necessary before running PCA-n2v. MSI data should than be transformed into a matrix (.npy) or better a sparse matrix (.npz) before further processing. Keep in mind that the format float16 is not supported in .npz matrixes.

For IonTOF systems, we recommend exporting all the data in .txt format. This creates as many files as are selected peaks. The function iontof_to_matrix has been especially implemented for this purpose.

For PHI data, we recommend exporting the data as .tif images in a dedicated folder. Warning: this functions only if the maximum value of pixels is 256, otherwise you might need to split one peak into several peaks. The function tif_to_matrix performs the task of turning a set of .tif images into a matrix.

We have not implemented functions for other systems but we will be very happy to include the functions you build for your own data into this Github as a service to the community.

Owner

  • Name: CEA-MetroCarac
  • Login: CEA-MetroCarac
  • Kind: organization
  • Location: France

Metrology and Characterization activities at the French Alternative Energies and Atomic Energy Commission

GitHub Events

Total
  • Public event: 1
  • Push event: 8
  • Pull request review event: 3
  • Pull request event: 4
  • Create event: 2
Last Year
  • Public event: 1
  • Push event: 8
  • Pull request review event: 3
  • Pull request event: 4
  • Create event: 2

Dependencies

requirements.txt pypi
  • ipywidgets *
  • matplotlib *
  • notebook *
  • numpy <2
  • pandas *
  • scikit-image *
  • scikit-learn *
  • scipy *
  • tensorflow <2.16
  • tifffile *
  • tqdm *
  • typing_extensions *