Skip to main content

Toolkit for Object Detection Distillation

Project description

Toolkit for Object Detection Distillation

_/_/_/_/_/                _/        _/
   _/      _/_/      _/_/_/    _/_/_/
  _/    _/    _/  _/    _/  _/    _/
 _/    _/    _/  _/    _/  _/    _/
_/      _/_/      _/_/_/    _/_/_/

docs lint test publish

codecov PyPI PyPI - Downloads wakatime

Contributor Covenant

Installation

Prerequisites:

  • torch
  • torchvision
  • mmcv/mmcv_full (optional)
pip install todd_ai

Developer Guides

pip install .\[dev,doc,test\]

TODO

  1. Complete repr, especially for runners
  2. mypy supports recursive types
  3. add a script to prepare imagenet dataset
  4. add Any to all missing typing fields
  5. make loss registry a sub-registry of model registry
  6. refactor registries
  7. remove odpsrun

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

todd_ai-0.5.1.tar.gz (85.4 kB view details)

Uploaded Source

Built Distribution

todd_ai-0.5.1-py3-none-any.whl (129.6 kB view details)

Uploaded Python 3

File details

Details for the file todd_ai-0.5.1.tar.gz.

File metadata

  • Download URL: todd_ai-0.5.1.tar.gz
  • Upload date:
  • Size: 85.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/5.0.0 CPython/3.12.3

File hashes

Hashes for todd_ai-0.5.1.tar.gz
Algorithm Hash digest
SHA256 cb50529ee7e0be9c5579022a8aa7916505f7ed3fdeec032bfaf998a7aa4987b2
MD5 7cb922dc91a8cf358f64e9bf1ae10a11
BLAKE2b-256 f90bcff218188ab72f0a1ea841a88dfa21a3cdc7fc46511c3adc804e70a583b3

See more details on using hashes here.

File details

Details for the file todd_ai-0.5.1-py3-none-any.whl.

File metadata

  • Download URL: todd_ai-0.5.1-py3-none-any.whl
  • Upload date:
  • Size: 129.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/5.0.0 CPython/3.12.3

File hashes

Hashes for todd_ai-0.5.1-py3-none-any.whl
Algorithm Hash digest
SHA256 b6beaeb0bec14480a3443c003619e5dc7eb16688e085d01471cbad266b06c496
MD5 5be3a73c5aa8bf8b474770022002c98a
BLAKE2b-256 44940bf2dcade2cbb14fbbfa1d5227cf570e9875854af13e4e6afabff1c12feb

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