torchpq - v0.3.0.1

- Cuda
Published by DeMoriarty over 3 years ago

torchpq - v0.3.0

Improvements on IVFPQ added DistributedCellContainer

- Cuda
Published by DeMoriarty over 4 years ago

torchpq - v0.2.0.2

Small improvements

- Cuda
Published by DeMoriarty over 4 years ago

torchpq - v0.2.0

What's new in v0.2.0?

1. IVFPQIndex search speed is greatly improved, now at least 2 times faster than before

2. IVFPQIndex now supports encoding residuals, pass pquseresidual=True to initializer method in order to toggle residual encoding on. this improves recall rate, espcially for low code sizes. You can see the difference between residual encoding on and off from benchmark results

3. Added new submodules, such as index, clustering, codec, transform and more

4. old implementations from v0.1 are moved to torchpq/legacy/

5. more thorough benchmark results on sift1m dataset

- Cuda
Published by DeMoriarty over 4 years ago

torchpq - v0.1.4

- Cuda
Published by DeMoriarty about 5 years ago