DrCyZ: Techniques for analyzing and extracting useful information from CyZ.

DrCyZ: Techniques for analyzing and extracting useful information from CyZ.

Samples from NASA Perseverance and set of GAN generated synthetic images from Neural Mars.

Repository: https://github.com/decurtoidiaz/drcyz

Subset of samples from (includes tools to visualize and analyse the dataset):

CyZ: MARS Space Exploration Dataset. [https://doi.org/10.5281/zenodo.5655473]

Images from NASA missions of the celestial body.

Repository: https://github.com/decurtoidiaz/cyz

Authors:

J. de Curtò c@decurto.be

I. de Zarzà z@dezarza.be

------------------------------------------
File Information from DrCyZ-1.0
------------------------------------------

    • Subset of samples from Perseverance (drcyz/c).
        ∙ png (drcyz/c/png).
            PNG files (5025) selected from NASA Perseverance (CyZ-1.1) after t-SNE and K-means Clustering.  
        ∙ csv (drcyz/c/csv).
            CSV file.

    • Resized samples from Perseverance (drcyz/c+).
        ∙ png 64x64; 128x128; 256x256; 512x512 (drcyz/c+/drcyz_64-512).
            PNG files resized at the corresponding size.  
        ∙ TFRecords 64x64; 128x128; 256x256; 512x512 (drcyz/c+/tfr_drcyz_64-512).
            TFRecord resized at the corresponding size to import on Tensorflow.

    • Synthetic images from Neural Mars generated using Stylegan2-ada (drcyz/drcyz+).
        ∙ png 100; 1000; 10000 (drcyz/drcyz+/drcyz_256_100-10000)
            PNG files subset of 100, 1000 and 10000 at size 256x256.

    • Network Checkpoint from Stylegan2-ada trained at size 256x256 (drcyz/model_drcyz).
        ∙ network-snapshot-000798-drcyz.pkl

    • Notebooks in python to analyse the original dataset and reproduce the experiments; K-means Clustering, t-SNE, PCA, synthetic generation using Stylegan2-ada and instance segmentation using Deeplab (https://github.com/decurtoidiaz/drcyz/tree/main/dr_cyz+).
        ∙ clustering_curiosity_de_curto_and_de_zarza.ipynb
            K-means Clustering and PCA(2) with images from Curiosity.
        ∙ clustering_perseverance_de_curto_and_de_zarza.ipynb
            K-means Clustering and PCA(2) with images from Perseverance.
        ∙ tsne_curiosity_de_curto_and_de_zarza.ipynb
            t-SNE and PCA (components selected to explain 99% of variance) with images from Curiosity.
        ∙ tsne_perseverance_de_curto_and_de_zarza.ipynb
            t-SNE and PCA (components selected to explain 99% of variance) with images from Perseverance.
        ∙ Stylegan2-ada_de_curto_and_de_zarza.ipynb
            Stylegan2-ada trained on a subset of images from NASA Perseverance (DrCyZ).
        ∙ statistics_perseverance_de_curto_and_de_zarza.ipynb
            Compute statistics from synthetic samples generated by Stylegan2-ada (DrCyZ) and images from NASA Perseverance (CyZ).
        ∙ DeepLab_TFLite_ADE20k_de_curto_and_de_zarza.ipynb
            Example of instance segmentation using Deeplab with a sample from NASA Perseverance (DrCyZ).