dlk: Deep Learning Kit
Project description
A Deep Learning ToolKit
This project is WIP.
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
- NLP
-
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
Release history Release notifications | RSS feed
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)
Built Distributions
dlk-0.0.16-py3.9.egg
(599.6 kB
view details)
dlk-0.0.16-py3.7.egg
(599.5 kB
view details)
dlk-0.0.16-py3-none-any.whl
(315.1 kB
view details)
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
Algorithm | Hash digest | |
---|---|---|
SHA256 | 015096258de07c176fada2ea090a9c884de59c398383f0239a73e78a917a4da9 |
|
MD5 | 7b0da8a7dde8ebd9708978ad46fdd92d |
|
BLAKE2b-256 | 09121c931ffad939c52d65285782123daa850c524f636aac2a38626c03826afa |
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
Algorithm | Hash digest | |
---|---|---|
SHA256 | f0522e6bf9f39dac6447aaf81bcfb76f4863359c8d7c18bef2098914daeae1c5 |
|
MD5 | 0a862fd4a8b8aeb3983487a6360b789b |
|
BLAKE2b-256 | 9999d0eb4112a121d86a673e3ddfb4fad3d7fab5286626695e982a6f647626a8 |
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
Algorithm | Hash digest | |
---|---|---|
SHA256 | 2da2f29f206c2fd7ef1ea944bc8df82c5c2c6fb4ee79b729460ecef2d7821edc |
|
MD5 | 053b4a5add6579205efc4f01dec1825d |
|
BLAKE2b-256 | c37c79936d7ed3fe6401ab562965f3e3ec643877ccd387dbf5e0f6f319591313 |
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
Algorithm | Hash digest | |
---|---|---|
SHA256 | 7c283ad429688e73cefd2bfb58f93f47b9949cf41f8837a86f3ec100306b1a5b |
|
MD5 | fa8e7bd2565ad191e8df763252089c5e |
|
BLAKE2b-256 | a10c081ec4c0b176aaaa0734bdba6f056e26b3119e956fa1923751a377a0bdc1 |