Open alexgarel opened 2 years ago
The approximate nearest neighbour world is innovating a lot those years.
Annoy is far from being the best. See https://github.com/erikbern/ann-benchmarks
Change the ANN library for one of this.
Perf that interest us are on large dataset (we have more than 10M images) in cosine distance.
And with a high embedding dimension (~800 for CLIP models).
The approximate nearest neighbour world is innovating a lot those years.
Annoy is far from being the best. See https://github.com/erikbern/ann-benchmarks
Change the ANN library for one of this.
Perf that interest us are on large dataset (we have more than 10M images) in cosine distance.