Model and Datasets

Pre-trained models and training datasets are licensed under a modified Apache license for non-commercial academic use only. An API key for accessing datasets and models can be obtained at https://users.deepcell.org/login/.

API Key Usage

The token that is issued by https://users.deepcell.org should be added as an environment variable:

export DEEPCELL_ACCESS_TOKEN=<token-from-users.deepcell.org>

This line can be added to your shell configuration (e.g. .bashrc, .zshrc, .bash_profile, etc.) to automatically grant access to DeepCell models/data upon login.

Model Weights

Pre-trained model weights are required to run the inference pipeline. These will be automatically downloaded to $HOME/.deepcell/models the first time you run cellsam_pipeline().

Alternatively, you can call get_model without any arguments to download the latest pre-trained model weights.

Training Data

Warning

The training dataset is around 14GB - make sure you have space and sufficient network bandwidth before attempting to download.

Similarly, training data can be downloaded for local use with:

>>> from cellSAM import download_training_data

>>> download_training_data()

The compressed dataset will be stored at $HOME/.deepcell/data/cellsam/.