Simulated industrial CT dataset for deep learning with dual-energy tomograms and ground truth material maps for copper and iron

We use this dataset for training and evaluation of a deep learning model to discriminate multi-material systems with X-ray CT. The dataset consists of: inputs: dual-energy tomograms as binary files without a header (tensor <strong>shape for numpy: 2x128x128 @float32</strong>) simulated spectra are 250kVp and 450kVp both prefiltered using 2mmCuSn outputs: the material maps a.k.a. ground truths for the training (same shape as inputs) sampled with a delaunay algorithm and randomly filled with iron and copper fractions The <strong>dataset is normalized to [0, 1]</strong>, so you have to multiply by the mass densities of copper and iron to obtain effective fractions in g/cm^3.