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

Note : this module requires at elast Python 3.8 to work.

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-0.1.1.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-0.1.1-py3-none-any.whl (45.1 MB view details)

Uploaded Python 3

File details

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

File metadata

  • Download URL: kpredict-0.1.1.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-0.1.1.tar.gz
Algorithm Hash digest
SHA256 4df55d7d233c3ca8ab6170474db8d57fe5d6f0dcb45dd44acefe9103708b25d8
MD5 0468fb102a552b73f4ef2ea30074b6aa
BLAKE2b-256 74b59a31dee576e9bf0eac79012d3ac0d32fd6aad93d25502d06c1b39c4edbe4

See more details on using hashes here.

File details

Details for the file kpredict-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: kpredict-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 45.1 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-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 a0cada1c82bd245f14b4d46a20d2c4edb3a4f1334879cf5f3bb0905c19bba03f
MD5 29eeb7ba210ea16ae6ed19f0acea9335
BLAKE2b-256 91633a2ed210383d2656b3d201f535800aa94acac2c75466d925631d2ca852a2

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