Training and test data, plus saved models for the paper "Top-down effects in an early visual cortex inspired hierarchical Variational Autoencoder" submitted to the SVRHM 2022 Workshop @ NeurIPS

<p>Each .pkl&nbsp;file contains a training or test dataset&nbsp;in the form of a Python dictionary (generated with Python 3.8.5) with the following fields:</p><ul><li>'train_images': 640,000 float32 images&nbsp;used&nbsp;for model training. 20px images contain 400 pixel intensities, 40px images contain 1600 pixel intensities each.</li><li>'train_labels': float32 labels for each image in&nbsp;'train_images'. All natural images are&nbsp;labeled&nbsp;with 0.0. Texture images are labeled with 0.0, 1,0, 2.0, 3.0, or 4.0,&nbsp;according to their texture family.</li><li>'test_images': 64,000 float32 images&nbsp;used&nbsp;for model testing.&nbsp;20px images contain 400 pixel intensities, 40px images contain 1600 pixel intensities each.</li><li>'test_labels': float32 labels for each image in&nbsp;'test_images'. All natural images are&nbsp;labeled&nbsp;with 0.0. Texture images are labeled with 0.0, 1,0, 2.0, 3.0, or 4.0,&nbsp;according to their texture family.</li></ul><p>Each .zip file contains a saved model.&nbsp;Details on these are coming soon.</p><p>For more details, see the paper&nbsp;"Top-down effects in an early visual cortex inspired hierarchical Variational Autoencoder" published at the SVRHM 2022 Workshop @ NeurIPS&nbsp;(<a href="https://openreview.net/forum?id=8dfboOQfYt3">link</a>).</p>