- <p class='welcome'>This page visualizes a large image collection within an interactive WebGL scene. Each image was processed with an <a href='https://www.cs.unc.edu/~wliu/papers/GoogLeNet.pdf' target='_blank'>Inception</a> Convolutional Neural Network, trained on <a href='http://image-net.org/challenges/LSVRC/2012/' target='_blank'>ImageNet 2012</a>, and projected into a two-dimensional manifold with the <a href='https://github.com/lmcinnes/umap' target='_blank'>UMAP</a> algorithm such that similar images appear proximate to one another.</p>
0 commit comments