description
Project description
:rocket: ANN :facepunch:
Install
pip install fast-ann
Usage
from ann import ANN
import numpy as np
data = np.random.random((1000, 128)).astype('float32')
ann = ANN()
ann.train(data, index_factory='IVF4000, Flat', noramlize=True)
dis, idx = ann.search(data[:10])
print(dis)
print(idx)
-
faiss不同量级对应的训练时间及内存测试
-
压缩方式测试
-
四种组合:默认是查向量返回 distance与index
- id => id/vector
- vector => id/vector
- push场景需要 docid => title_vector => docid
-
线上服务
- id2word
- id2vector
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Close
Hashes for fast-ann-2019.12.9.21.49.14.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 232743cecd8beddb26d009140299472d41cc4155156e0fa0226cec4a1e16a9e0 |
|
MD5 | 32e77f240e96515636a00a445ae08f88 |
|
BLAKE2b-256 | b15a8e2877ac1d8735b478abd7fcda0609ca5f680fee10e8ae3a1c0f96d01ada |
Close
Hashes for fast_ann-2019.12.9.21.49.14-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 819f7b45cbfbf4fd3ce6b40589b45fdb4edd2521aefb1d4bff3dc25292c614f4 |
|
MD5 | 388b44061f8ad403afae76b1f20f8ca1 |
|
BLAKE2b-256 | 3206d04e29f38d1d67946232d14ee7344a3eb4bc908805d1c37dcd82b76dde66 |