Image Synthesis with a Convolutional Capsule Generative Adversarial Network- Prepared Data

<p>A set of prepared datasets for running experiments to replicate paper (see below).</p> <p>List of data:</p> <p>Training capspix2pix:</p> <ul> <li>crops256.zip - folder containing 256x256 crops from the original dataset for training capspix2pix. Images are in the &quot;train/original&quot; folder, and labels are in the &quot;train/mask&quot; folder.</li> <li>syn256_x_data_val.npy + syn256_y_data_val.npy + syn256_y_points_data_val.npy (images + labels + centrelines) - validation synthetic dataset, used while training capspix2pix for plotting</li> </ul> <p>Training u-net:</p> <ul> <li>capspix2pix_AR_data_train.npy + capspix2pix_AR_mask_train.npy (images + labels) - data generated from a capspix2pix model from real labels</li> <li>capspix2pix_SSM_data_train.npy + capspix2pix_AR_mask_train.npy (images + labels) - data generated from a capspix2pix model from synthetic labels</li> <li>PBAM_SSM_data_train.npy + PBAM_SSM_mask_train.npy (images + labels) - data generated from PBAM (Physics-based model) for training u-net</li> <li>pix2pix_AR_data_train.npy + pix2pix_AR_mask_train.npy (images + labels) - data generated from a pix2pix model from real labels for training u-net</li> <li>pix2pix_SSM_data_train.npy + pix2pix_SSM_mask_train.npy (images + labels) - data generated from a pix2pix model from synthetic labels for training u-net</li> <li>real_data_data_train.npy + real_data_mask_train.npy (images + labels) - augmented real dataset for training u-net</li> </ul> <p>Testing u-net:</p> <ul> <li>org64_data_test.npy + org64_mask_test.npy (images + labels) - crops from original test dataset for testing u-net</li> </ul> <p>Interpolation:</p> <ul> <li>crops256_inter_data_train.npy + crops256_inter_mask_train.npy (images + labels) - example data for interpolation</li> </ul> <p><strong>Please cite the following paper when using this dataset:</strong></p> <p>Bass, C.,&nbsp;Dai, T., Billot,&nbsp;B.,&nbsp;&nbsp;Arulkumaran,&nbsp;K.,&nbsp;Creswell, A.,&nbsp;Clopath,&nbsp;C.,&nbsp;De Paola,&nbsp;V., and&nbsp;Bharath,&nbsp;A. A., 2019. &ldquo;Image synthesis with a convolutional capsule generative adversarial network,&rdquo;&nbsp;<em>Medial Imaging with Deep Learning.</em></p> <p><strong>See Github page for further instructions:</strong></p> <p>https://github.com/CherBass/CapsPix2Pix</p> <p>&nbsp;</p>