cellmap-models

Repository of model architectures and network weights used for CellMap segmentations.


Keywords
machine, learning, deep, cell, segmentation, cellpose, cellmap, machine-learning
License
BSD-1-Clause
Install
pip install cellmap-models==0.1.0

Documentation

GitHub Org's stars

CellMap logo

cellmap-models

GitHub Downloads (all assets, all releases) GitHub License Python Version from PEP 621 TOML

tests black mypy codecov

This package contains the models used for segmention by the CellMap project team at HHMI Janelia.

Installation

We strongly recommend installing within a conda (or mamba) environment to install the package.

conda env create -y -n cellmap python=3.10 pytorch -c pytorch
conda activate cellmap
pip install cellmap-models

Usage

import cellmap_models

Different models are available in the cellmap-models module. For example, to use the models produced by the COSEM pilot project team, and published as part of Whole-cell organelle segmentation in volume electron microscopy:

import cellmap_models.cosem as cosem_models
print(cosem_models.models_list)

This will list the available models. To load a specific model, use the load_model function:

model = cosem_models.load_model('setup04/1820500')

More information on each set of models and how to use them is available in the README.md file in the corresponding subdirectory.