https://github.com/biointelligence-lab/imflow

ImFlow: A better image dataset loader for TensorFlow

https://github.com/biointelligence-lab/imflow

Science Score: 13.0%

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
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (9.1%) to scientific vocabulary

Keywords

deep-learning machine-learning medical medical-image-processing medical-imaging medical-imaging-classification medical-imaging-datasets tensorflow
Last synced: 9 months ago · JSON representation

Repository

ImFlow: A better image dataset loader for TensorFlow

Basic Info
Statistics
  • Stars: 0
  • Watchers: 3
  • Forks: 0
  • Open Issues: 1
  • Releases: 0
Topics
deep-learning machine-learning medical medical-image-processing medical-imaging medical-imaging-classification medical-imaging-datasets tensorflow
Created over 3 years ago · Last pushed almost 3 years ago
Metadata Files
Readme License Code of conduct

README.md

ImFlow

What is ImFlow?

A better image dataset loader for TensorFlow.

ImFlow is an open source Python library for working with large-scale medical imaging datasets in TensorFlow. It extends TensorFlow's capability for dynamically loading imaging data by providing a quick interface for creating tf.Dataset objects from dataframes, CSV files, and manually.

Getting Started

ImFlow is currently not available through pip, but you can manually install it.

Manual Installation

You can manually install ImFlow as follows:

bash $ git clone https://github.com/UM2ii/imflow $ pip install imflow/

Documentation

imflow.image_dataset_from_directory

imflow.image_dataset_from_csv

imflow.image_dataset_from_dataframe

imflow.image_dataset_from_paths_and_labels

Roadmap

We are still working on expanding the capabilities of ImFlow. Here's a quick look at what to expect from future versions of ImFlow!

  • Complete documentation and usage with examples and tests
  • Built-in data preprocessing and augmentation pipelines (with support for custom pipelines)
  • Extended support for DICOM and NifTI file formats
  • Support for loading bounding boxes and segmentation masks as labels
  • Support for 3D imaging data

Owner

  • Name: BioIntelligence-Lab
  • Login: BioIntelligence-Lab
  • Kind: organization

GitHub Events

Total
Last Year

Dependencies

setup.py pypi
  • nibabel *
  • numpy *
  • pandas *
  • pydicom *
  • tensorflow >=2.7
  • tensorflow_io >=0.23