Skip to main content

A library to calculate sharpness value of loss-landscapes

Project description

landscapelaser

Implementation of the landscapelaser PyPi package.

Calculates sharpness of the loss landscape of a model.

Use

To use the package, do:

from landscapelaser import LandscapeLaser
ll = LandscapeLaser()

import numpy as np
arr = np.random.random((20,20))

sharpness, mean_loss = ll.calculate(values=arr)
print(
    f'The sharpness measure of the loss landscape is `{sharpness}`'
    f' with mean loss over the landscape equal to `{mean_loss}`'
)

Here, arr is a 2d numpy array containing the loss values in the landscape. To calculate this, refer to loss-landscapes package.

Installation

The package is available on PyPI. Install using:

pip install landscapelaser

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

landscapelaser-0.1.1.tar.gz (4.0 kB view details)

Uploaded Source

File details

Details for the file landscapelaser-0.1.1.tar.gz.

File metadata

  • Download URL: landscapelaser-0.1.1.tar.gz
  • Upload date:
  • Size: 4.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.6

File hashes

Hashes for landscapelaser-0.1.1.tar.gz
Algorithm Hash digest
SHA256 a53a88f37cc570aca19a8b3a5cbba39e61d307fdcb897df928f38a4bca4c076f
MD5 4052a9e60f363b21356c212af739a920
BLAKE2b-256 abb81b2af57dadabe5fe41cabf0b126df13d888b7b02df5e43f55f849f0a518d

See more details on using hashes here.

Supported by

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