Skip to main content

Implementation of various EDL loss functions

Project description

EDL Losses for CSI-VAE

A research library implementing some Evidential Deep Learning (EDL) loss functions available in the literature.

Currently the losses from the following papers are implemented:

Getting Started

Prerequisites

  • Python 3.13+

Installation

Clone the parent repository and navigate to this module:

git clone <repo-url>
cd csi_vae/edl_losses
pip install -r requirements.txt

Usage

from losses import edl_loss

# Example usage
loss = edl_loss(predictions, targets, epoch)
loss.backward()

License

MIT. See LICENSE.

Author

Luca Cotti (luca.cotti@unibs.it)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

edl_losses-0.1.0.tar.gz (3.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

edl_losses-0.1.0-py3-none-any.whl (5.4 kB view details)

Uploaded Python 3

File details

Details for the file edl_losses-0.1.0.tar.gz.

File metadata

  • Download URL: edl_losses-0.1.0.tar.gz
  • Upload date:
  • Size: 3.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.11.7 {"installer":{"name":"uv","version":"0.11.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for edl_losses-0.1.0.tar.gz
Algorithm Hash digest
SHA256 dc1ffb567d90dbbd06565a3acf875bd3148e9efb3b4e964b00852b2b51494b7c
MD5 070d924ddd72dd1f7dfc9b3e45b95ad4
BLAKE2b-256 eef0658d79b5fcf5b6dd9cb836751206e4f8c5fddaee5abaab9cd630feec5b89

See more details on using hashes here.

File details

Details for the file edl_losses-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: edl_losses-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 5.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.11.7 {"installer":{"name":"uv","version":"0.11.7","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for edl_losses-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 9b220267fac9a0cf849509ce16bc585bbb9db4ee6943c252bd100c09bbdaf870
MD5 4328cd4b4218d4291424b114791e660f
BLAKE2b-256 b681b9cd57db227425d1e59ae1852ae0c5e26b460e533119bbe3279e82cda63a

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page