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-2019.12.9.18.0.18.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 3a4d601dba0bda675fb02fc52258d5151f17e8d539bf527184f97063a958047d |
|
MD5 | c1286a6f17a8b7e64d0bb75386cac643 |
|
BLAKE2b-256 | bfd615f72df0a34511acb9414432205d97e5130f7e6f4c07d8ed560de4bb332b |
Close
Hashes for fast_ann-2019.12.9.18.0.18-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 02729c23cf0d5ac4ce0d45285152c199ce4dc197b12431b06ddf4b2efe58bd27 |
|
MD5 | 06510425b95210e4c8e5dafebdee7a51 |
|
BLAKE2b-256 | 4b078d66c753d311554da2b19e59a88b58b73ced3e6a23e8e126e56f920a2762 |