Predict Tomogram Embeddings with SwinUNETR using Copick API and generate the tensorboard files

Apply a SwinUNETR model to a tomogram fetched using the Copick API to produce embeddings, and save them in a Zarr.

Arguments

--copick_config_path

Path to the Copick configuration JSON file. (default value: PARAMETER_VALUE)

--run_name

Name of the Copick run to process. (default value: PARAMETER_VALUE)

--voxel_spacing

Voxel spacing to be used. (default value: PARAMETER_VALUE)

--tomo_type

Type of tomogram to process. (default value: PARAMETER_VALUE)

--checkpointpath

Path to the checkpoint file of the trained SwinUNETR model (default value: PARAMETER_VALUE)

--embedding_name

Name of the embedding to use as the feature name in Copick (default value: PARAMETER_VALUE)

Please follow this link for details on how to install and run this solution.