PyTorch module for random projection hashing
Project description
Random Projection Hashing
Provides a PyTorch module for random projection hashing with GPU acceleration. Similar tensors (cosine similarity) will be assigned the same hash with high probability.
Installation
$ pip install rph
Usage
See example.py for an example on how to use rph on DNA strings. Please note that rph can be used with any arbitrary tensors. In summary, this package provides a module RandomProjectionHashModule(input_dim, hash_bits) where input_dim is the size of the input tensors and hash_bits is the number of bits to use for the final hash value. For example, choosing 4 bits will result in all tensors being split into 16 buckets only.
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
File details
Details for the file rph-1.0.0.tar.gz.
File metadata
- Download URL: rph-1.0.0.tar.gz
- Upload date:
- Size: 2.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.1.1 pkginfo/1.5.0.1 requests/2.22.0 setuptools/45.2.0 requests-toolbelt/0.9.1 tqdm/4.32.1 CPython/3.7.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | fefb73a979bcaee910fb6c63cb649d187bcabd425b47fce3578031012a4be1fe |
|
| MD5 | dc3156d0595e19c9c333a2772b67241b |
|
| BLAKE2b-256 | 9b673c941b21c7db3be5de8babebcf5e714806d949f7065e6fbf23ae9efab399 |
File details
Details for the file rph-1.0.0-py3-none-any.whl.
File metadata
- Download URL: rph-1.0.0-py3-none-any.whl
- Upload date:
- Size: 3.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.1.1 pkginfo/1.5.0.1 requests/2.22.0 setuptools/45.2.0 requests-toolbelt/0.9.1 tqdm/4.32.1 CPython/3.7.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 8f8da4ff560f4a54c3c9d19a2c2554ad7e9b662c305195ad55fc5b93ce8e3a99 |
|
| MD5 | 32184be27bdd68ead8f391f00101f8e1 |
|
| BLAKE2b-256 | 3a3c347871765ae49b6851194adf0013fc63c506f852dc9124a0e8e73702559f |
