Skip to main content

dlk: Deep Learning Kit

Project description

A Deep Learning ToolKit

This project is WIP.

Read the Docs

Install

pip install dlk

or 
git clone this repo and do

python setup.py install

What's this?

  • Provide a templete for deep learning (especially for nlp) training and deploy.
  • Provide parameters search.
  • Provide basic architecture search.
  • Provide some basic modules and models.
  • Provide reuse the pretrained model for predict.

More Feature is Comming

  • Tasks support
    • NLP
      • Classification
      • Pair Classification
      • Regression
      • Pair Regression
      • Sequence Labeling
      • Span Classification
      • Relation Extraction
      • Token Rerank
      • MRC SQuAD
      • Translation
      • Summary
    • CV
      • Classification
  • Generate models.

  • Distill structure.

  • Ensemble models for NLU(and check how to do this in NLG)

  • Training Strategy

    • Adversarial Training(FGM/PGD/FreeLB)
    • Schedule Loss(you can control the loss schedule)
    • Schedule MultiTask Loss(you can control the loss schedule for each task)
    • Focal Loss
  • Online service by triton.

  • Data Augment.

  • Support LightGBM. Will split to another package.

  • Make most complexity modules like Beam Search, CRF to be scriptable.

  • Add UnitTest

    • Parser
    • Tokenizer
    • Config
    • Link

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

dlk-0.0.16.tar.gz (150.0 kB view details)

Uploaded Source

Built Distributions

dlk-0.0.16-py3.9.egg (599.6 kB view details)

Uploaded Egg

dlk-0.0.16-py3.7.egg (599.5 kB view details)

Uploaded Egg

dlk-0.0.16-py3-none-any.whl (315.1 kB view details)

Uploaded Python 3

File details

Details for the file dlk-0.0.16.tar.gz.

File metadata

  • Download URL: dlk-0.0.16.tar.gz
  • Upload date:
  • Size: 150.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.0 CPython/3.9.7

File hashes

Hashes for dlk-0.0.16.tar.gz
Algorithm Hash digest
SHA256 015096258de07c176fada2ea090a9c884de59c398383f0239a73e78a917a4da9
MD5 7b0da8a7dde8ebd9708978ad46fdd92d
BLAKE2b-256 09121c931ffad939c52d65285782123daa850c524f636aac2a38626c03826afa

See more details on using hashes here.

File details

Details for the file dlk-0.0.16-py3.9.egg.

File metadata

  • Download URL: dlk-0.0.16-py3.9.egg
  • Upload date:
  • Size: 599.6 kB
  • Tags: Egg
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.0 CPython/3.9.7

File hashes

Hashes for dlk-0.0.16-py3.9.egg
Algorithm Hash digest
SHA256 f0522e6bf9f39dac6447aaf81bcfb76f4863359c8d7c18bef2098914daeae1c5
MD5 0a862fd4a8b8aeb3983487a6360b789b
BLAKE2b-256 9999d0eb4112a121d86a673e3ddfb4fad3d7fab5286626695e982a6f647626a8

See more details on using hashes here.

File details

Details for the file dlk-0.0.16-py3.7.egg.

File metadata

  • Download URL: dlk-0.0.16-py3.7.egg
  • Upload date:
  • Size: 599.5 kB
  • Tags: Egg
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.0 CPython/3.9.7

File hashes

Hashes for dlk-0.0.16-py3.7.egg
Algorithm Hash digest
SHA256 2da2f29f206c2fd7ef1ea944bc8df82c5c2c6fb4ee79b729460ecef2d7821edc
MD5 053b4a5add6579205efc4f01dec1825d
BLAKE2b-256 c37c79936d7ed3fe6401ab562965f3e3ec643877ccd387dbf5e0f6f319591313

See more details on using hashes here.

File details

Details for the file dlk-0.0.16-py3-none-any.whl.

File metadata

  • Download URL: dlk-0.0.16-py3-none-any.whl
  • Upload date:
  • Size: 315.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.0 CPython/3.9.7

File hashes

Hashes for dlk-0.0.16-py3-none-any.whl
Algorithm Hash digest
SHA256 7c283ad429688e73cefd2bfb58f93f47b9949cf41f8837a86f3ec100306b1a5b
MD5 fa8e7bd2565ad191e8df763252089c5e
BLAKE2b-256 a10c081ec4c0b176aaaa0734bdba6f056e26b3119e956fa1923751a377a0bdc1

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page