diff --git a/README.md b/README.md index d02dc8f07..6999c8fe0 100644 --- a/README.md +++ b/README.md @@ -75,6 +75,11 @@ We have a number of precomputed data sets in HDF5 format. All data sets have bee | [Last.fm](https://github.com/erikbern/ann-benchmarks/pull/91) | 65 | 292,385 | 50,000 | 100 | Angular | [HDF5](http://ann-benchmarks.com/lastfm-64-dot.hdf5) (135MB) | | [COCO-I2I](https://cocodataset.org/) | 512 | 113,287 | 10,000 | 100 | Angular | [HDF5](https://github.com/fabiocarrara/str-encoders/releases/download/v0.1.3/coco-i2i-512-angular.hdf5) (136MB) | | [COCO-T2I](https://cocodataset.org/) | 512 | 113,287 | 10,000 | 100 | Angular | [HDF5](https://github.com/fabiocarrara/str-encoders/releases/download/v0.1.3/coco-t2i-512-angular.hdf5) (136MB) | +| Dataset | Dimensions | Train size | Test size | Neighbors | Distance | Download | +|---------|-----------:|-----------:|----------:|----------:|----------|----------| +| Wikipedia-1024 | 1024 | 1,000,000,000 | 10,000 | 100 | Angular | [HDF5](https://your-host.com/wikipedia-1024-angular.hdf5) | +| Wikipedia-4096 | 4096 | 1,000,000,000 | 10,000 | 100 | Angular | [HDF5](https://your-host.com/wikipedia-4096-angular.hdf5) | +| Wikipedia-8192 | 8192 | 1,000,000,000 | 10,000 | 100 | Angular | [HDF5](https://your-host.com/wikipedia-8192-angular.hdf5) | Results ======= diff --git a/ann_benchmarks/datasets.py b/ann_benchmarks/datasets.py index 8b3278785..217437cbf 100644 --- a/ann_benchmarks/datasets.py +++ b/ann_benchmarks/datasets.py @@ -598,6 +598,23 @@ def coco(out_fn: str, kind: str): DATASETS: Dict[str, Callable[[str], None]] = { + + "wikipedia-1024-angular": { + 'url': 'https://your-host.com/wikipedia-1024-angular.hdf5', + 'constructor': Dataset, + 'base': 'wikipedia-1024-angular.hdf5' + }, + "wikipedia-4096-angular": { + 'url': 'https://your-host.com/wikipedia-4096-angular.hdf5', + 'constructor': Dataset, + 'base': 'wikipedia-4096-angular.hdf5' + }, + "wikipedia-8192-angular": { + 'url': 'https://your-host.com/wikipedia-8192-angular.hdf5', + 'constructor': Dataset, + 'base': 'wikipedia-8192-angular.hdf5' + }, + "deep-image-96-angular": deep_image, "fashion-mnist-784-euclidean": fashion_mnist, "gist-960-euclidean": gist,