Source Data for: Generative learning of morphological and contrast heterogeneities for self-supervised electron micrograph segmentation

Related data for EMcopilot. Below is the hierarchical structure of the dataset. If you are using this dataset in your publication, please cite our paper:  npj Comput. Mater. 11, 322 (2025). https://doi.org/10.1038/s41524-025-01800-5.

Declare: EMcopilot has been registered as a trademark by the Intellectual Property Office of Singapore, No. 40202319264T.

- EMcopilot_dataset/

    - 01_experimental_images/

        - 01_01_PtSn_Al2O3_nanoparticle/

        - 01_02_PtSn_Al2O3_cluster/

        - 01_03_Au_ZSM5/

    - 02_manual_labels/

        - 02_01_PtSn_Al2O3_nanoparticle/

        - 02_02_PtSn_Al2O3_cluster/

        - 02_03_Au_ZSM5/

    - 03_SAM_masks/

        - 03_01_PtSn_Al2O3_nanoparticle/

        - 03_02_PtSn_Al2O3_cluster/

    - 04_generated_masks/

        - 04_01_PtSn_Al2O3_nanoparticle/

    - 05_synthetic_images/

        - 05_01_PtSn_Al2O3_nanoparticle/

    - 06_adapted_images/

        - 06_01_PtSn_Al2O3_nanoparticle/

    - 07_model_checkpoints_pix2pix/

        - 07_01_PtSn_Al2O3_nanoparticle/

        - 07_02_PtSn_Al2O3_cluster/

        - 07_03_Au_ZSM5/

        - 07_04_Pd_C/

        - 07_05_SACs/

    - 08_model_checkpoints_CBAMUNet++/

        - 08_01_EMcopilot_trained/

        - 08_02_manual_labeling_trained/

        - 08_03_five_shot_hybrid__trained/