Skip to main content

Visualizing the beauty of neural networks

Project description

Handwritten-Character-Recognition

Unstable, dev version.

Installation

FAQ

Limitations

  • can only be used in fullscreen mode
  • the UI layout is specifically designed for 64x64 inputs and has 36 outputs
  • the UI layout is customized for the 1366x768 display size
  • The hidden layers are hardcoded with three layers (50, 40, 35)

Troubleshoot

  • To report bugs, please open an issue/pull request, or you can reach me here.

Changelog

  • 1.2.0 (June 13, 2023):

    Motivation: To provide a cleaner UI and restructure the codebase.

    • Removed feature: uptime display
    • Removed feature: metadata display (the one in the TL corner)
    • Removed feature: datasets stats display (the one in the TR corner)
    • Removed feature: static labels ("64x64", "size: [...]")
    • File name changed: main/misc.py -> main/constants.py
    • Dependencies updates: mykit==1.0.0 -> mykit==2.0.2
    • Added 'settings' and 'CLI' feature
  • 1.1.0 (June 11, 2023):

    • removed carbon_plug, using mykit instead
  • v1.0.1 (May 10, 2023):

    • BUG FIXED: Renamed carbon to carbon_plug to prevent conflicts with the original carbon module (if installed).

License

This project is licensed under the MIT license.

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

hcr-1.2.0.dev1.tar.gz (16.6 kB view details)

Uploaded Source

Built Distribution

hcr-1.2.0.dev1-py3-none-any.whl (18.3 kB view details)

Uploaded Python 3

File details

Details for the file hcr-1.2.0.dev1.tar.gz.

File metadata

  • Download URL: hcr-1.2.0.dev1.tar.gz
  • Upload date:
  • Size: 16.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.3

File hashes

Hashes for hcr-1.2.0.dev1.tar.gz
Algorithm Hash digest
SHA256 76a8bb259733119e8d12eaccb6da4e1016dfc7596f542f68d4fbf349a3bfd36e
MD5 1f14f59fea5722b2a9f0f9dc4d83a488
BLAKE2b-256 fb591d49d5a9af311144ca1162be26d8e857b184db2066d32ad7aab5f6394967

See more details on using hashes here.

Provenance

File details

Details for the file hcr-1.2.0.dev1-py3-none-any.whl.

File metadata

  • Download URL: hcr-1.2.0.dev1-py3-none-any.whl
  • Upload date:
  • Size: 18.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.10.3

File hashes

Hashes for hcr-1.2.0.dev1-py3-none-any.whl
Algorithm Hash digest
SHA256 855dfaeecd38d35c45418d6c1b59db244770b20cac6743a1989b4e803127f972
MD5 6f910d6e21d1d9b15bb9ccde544c0e7b
BLAKE2b-256 ceaeb477956fb29103de47cba6956a16f717153b41613eb3bc4834be6b4565d9

See more details on using hashes here.

Provenance

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