# embeddings-sort This program can sort images such that ones with similar motives are close together. This is accomplished by using [AI](https://github.com/minimaxir/imgbeddings) to extract the meaning of the image, and then approximating a travelling-salesperson-tour through all of them. As a bonus feature, this program can also sort the images by hue, brightness or color, though the results for this could be improved by using a less generalized algorithm. The sorting can be accessed by letting the progam print the image paths in order, or by copying/symlinking the images into a new directory. Detailed usage: ``` Usage: embeddings-sort [OPTIONS] [IMAGES]... Arguments: [IMAGES]... Options: -e, --embedder Characteristic to sort by [default: content-euclidean] [possible values: brightness, hue, color, content-euclidean, content-angular-distance, content-manhatten] -s, --symlink-dir Symlink the sorted images into this directory -o, --copy-dir Copy the sorted images into this directory. Uses COW when available -c, --stdout Write sorted paths into stdout, one per line -0, --stdout0 Write sorted paths into stdout, null-separated. Overrides -c -b, --benchmark Output total tour length to stderr --tsp-approx Algorithm for TSP approximation. Leave as default if unsure [default: christofides] [possible values: mst-dfs, christofides, christofides-refined] -h, --help Print help ``` ## Insides The chrisofides implementation uses an approximated min-weight matching algorithm, which may be non-ideal, though I haven't benchmarked how much of a difference it makes (mainly due to the implementation complexity of an exact algorithm, which would also increase the implementations complexity from O(n²) to O(n³) where n is the number of given images). christofides-refined is planned to be christofides but with an O(n²) 2-opt-swapping step added after the main algorithm. Implementing this efficiently will also require some algorithmic trickery, so it's not ready yet.