Skip to main content

CLI image classification trainer with Gemini-driven hyperparameters and modern Keras backbones

Project description

classiloom

CLI trainer for image classification. Gemini proposes hyperparameters. Keras backbones (MobileNetV2, EfficientNetB0, ResNet50) or a compact CNN. No database. Artifacts and metrics saved under runs/.

Commands

  • classiloom set gemini_api <token>
  • classiloom set gemini_model <name>
  • classiloom scan <dataset_dir> --out runs
  • classiloom suggest <scan_json> --trials 8 --out runs
  • classiloom train <dataset_dir> <configs_json> --idx 0 --out runs [--mixed-precision] [--fine-tune]
  • classiloom predict <image_path> <model_dir>

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

classiloom-0.1.0.tar.gz (10.7 kB view details)

Uploaded Source

Built Distribution

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

classiloom-0.1.0-py3-none-any.whl (13.0 kB view details)

Uploaded Python 3

File details

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

File metadata

  • Download URL: classiloom-0.1.0.tar.gz
  • Upload date:
  • Size: 10.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.9.6

File hashes

Hashes for classiloom-0.1.0.tar.gz
Algorithm Hash digest
SHA256 84cd46f176505804f2f281fda506c2db1b45941a34f027321d60765f7aa4dab5
MD5 7d424ccc2540f80f834fcd635acfe115
BLAKE2b-256 2c5f794ff77f9ab803660a0eb56a5dc5387293e8e097abf0c5c7075bc70de3ee

See more details on using hashes here.

File details

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

File metadata

  • Download URL: classiloom-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 13.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.9.6

File hashes

Hashes for classiloom-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 8318df2d492bf7c791e81cfcfdcff091ccadb1723591c82992dccbc14161339e
MD5 ead23a72829e2b7ad0df1b6a2ab468cf
BLAKE2b-256 1f38efb067d421b45a96dda9f45ff9a406094b6bc7c261afbba23629d5eb105e

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