Skip to main content

No project description provided

Project description

Kpredict

Kpredict is a ptyhon library that can predict the size of the compiled vmlinux file given only a .config file using machine learning.

Usage

Kpredict is available on pip :

pip install kpredict

The straightest way to use it is to run the built-in script :

kpredict .config

Supported versions

With the help of transfer learning, multiple versions are supported :

  • 4.13
  • 4.15
  • 4.20
  • 5.0
  • 5.4
  • 5.7
  • 5.8

For now, the models are noly available for Linux/x86 version, using the compiler ggc version 6.3.0.

Accuracy

On version 5.8, the error rate is on average 5.2% of the real size, using Mean Absolute Percentage error, with a standard deviation of 5.63. The median is at 3.67%, meaning half the predictions are below this error rate. 97% of the predictions are below 20% error.

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

kpredict-0.1.0.tar.gz (44.6 MB view details)

Uploaded Source

Built Distribution

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

kpredict-0.1.0-py3-none-any.whl (45.0 MB view details)

Uploaded Python 3

File details

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

File metadata

  • Download URL: kpredict-0.1.0.tar.gz
  • Upload date:
  • Size: 44.6 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.3.0 pkginfo/1.7.0 requests/2.25.1 setuptools/53.0.0 requests-toolbelt/0.9.1 tqdm/4.56.2 CPython/3.8.7

File hashes

Hashes for kpredict-0.1.0.tar.gz
Algorithm Hash digest
SHA256 453ca9dc296cfaab1b75d49958db8d54c69e88293cc5a3185ba3f2ef647ad3e0
MD5 6db82c7536d7120a57c36fdb42608bc7
BLAKE2b-256 52f3629bbc994739cc89f2fbe42567fc9b358529dfa7e6b0a7a32e41eafb9c45

See more details on using hashes here.

File details

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

File metadata

  • Download URL: kpredict-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 45.0 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.3.0 pkginfo/1.7.0 requests/2.25.1 setuptools/53.0.0 requests-toolbelt/0.9.1 tqdm/4.56.2 CPython/3.8.7

File hashes

Hashes for kpredict-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 82aa49e0a99b82a44c831a55b03585b2368c8c41329bc1a2df303fcb62bdc3c4
MD5 1297ad43fe772d69521785550e6152e6
BLAKE2b-256 7a77e003995403eeacab977b90fe355fc892b90c5562daf6b3612c67c2719c6c

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