Metadata-Version: 2.1
Name: rph
Version: 1.0.0
Summary: PyTorch module for random projection hashing
Home-page: https://github.com/ag14774/rph.git
Author: Andreas Georgiou
Author-email: geandrea@ethz.ch
License: UNKNOWN
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.6
Description-Content-Type: text/markdown

# 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.


