TorchLikelihoods: User-friendly handling of likelihoods in Pytorch
Project description
TorchLikelihoods
A library for handling likelihoods in PyTorch for any type of data
Installation
Run the following to install
pip install torchlikelihoods
Usage
from torchlikelihoods import NormalLikelihood
import torch
num_samples, num_feats = 100, 5
normal_data = torch.randn((num_samples, num_feats))
lik = NormalLikelihood(domain_size=num_feats)
scaler = lik.get_scaler()
print(f"Domain size: {lik.domain_size()}")
print(f"Params size: {lik.params_size()}")
Do you want to get involved in the development?
pip install -e .[dev]
Testing
To run the tests:
make test
pytest
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
torchlikelihoods-0.0.6.1.tar.gz
(14.0 kB
view details)
Built Distribution
File details
Details for the file torchlikelihoods-0.0.6.1.tar.gz
.
File metadata
- Download URL: torchlikelihoods-0.0.6.1.tar.gz
- Upload date:
- Size: 14.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.10.4
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 9f5fc20c27ccaa3f30d10bddd334fd00de46d6ed36ecc3316dd4dc2612ec4303 |
|
MD5 | 1274b816d18fbdb6b4018097fca8f37a |
|
BLAKE2b-256 | 4d850f970d35283bcdca88c95c5baee039a1f1fbdcc309397a1ced5c9674be6e |
File details
Details for the file torchlikelihoods-0.0.6.1-py3-none-any.whl
.
File metadata
- Download URL: torchlikelihoods-0.0.6.1-py3-none-any.whl
- Upload date:
- Size: 26.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.10.4
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 10f89da07fec795a747997fa50319ccbfdb92db6f7560810973301a3be90fa3a |
|
MD5 | 2218686d48fd8d4e595d5ca860d7967b |
|
BLAKE2b-256 | a5cb70f1b792b83d35fa5d805ed26f9d13cc9fe2e536645ca42a4538bb526838 |