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
1 maintainer
Metadata
1 maintainer
Release files for dlk 0.0.16
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| dlk-0.0.16.tar.gz | 150.0 kB | Details |
Built distributions (wheels)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| dlk-0.0.16-py3.9.egg | Legacy Egg format | - | - | Details |
| dlk-0.0.16-py3.7.egg | Legacy Egg format | - | - | Details |
| dlk-0.0.16-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 1.7 MB
Release files / dlk-0.0.16.tar.gz
| Download URL | dlk-0.0.16.tar.gz |
|---|---|
| Size | 150.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
015096258de07c176fada2ea090a9c884de59c398383f0239a73e78a917a4da9
|
|
BLAKE2b-256 checksum How to use checksums |
09121c931ffad939c52d65285782123daa850c524f636aac2a38626c03826afa
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.0 CPython/3.9.7
|
Release files / dlk-0.0.16-py3.9.egg
| Download URL | dlk-0.0.16-py3.9.egg |
|---|---|
| Size | 599.6 kB |
| Tags | Egg |
|
SHA-256 checksum How to use checksums |
f0522e6bf9f39dac6447aaf81bcfb76f4863359c8d7c18bef2098914daeae1c5
|
|
BLAKE2b-256 checksum How to use checksums |
9999d0eb4112a121d86a673e3ddfb4fad3d7fab5286626695e982a6f647626a8
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.0 CPython/3.9.7
|
Release files / dlk-0.0.16-py3.7.egg
| Download URL | dlk-0.0.16-py3.7.egg |
|---|---|
| Size | 599.5 kB |
| Tags | Egg |
|
SHA-256 checksum How to use checksums |
2da2f29f206c2fd7ef1ea944bc8df82c5c2c6fb4ee79b729460ecef2d7821edc
|
|
BLAKE2b-256 checksum How to use checksums |
c37c79936d7ed3fe6401ab562965f3e3ec643877ccd387dbf5e0f6f319591313
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.0 CPython/3.9.7
|
Release files / dlk-0.0.16-py3-none-any.whl
| Download URL | dlk-0.0.16-py3-none-any.whl |
|---|---|
| Size | 315.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
7c283ad429688e73cefd2bfb58f93f47b9949cf41f8837a86f3ec100306b1a5b
|
|
BLAKE2b-256 checksum How to use checksums |
a10c081ec4c0b176aaaa0734bdba6f056e26b3119e956fa1923751a377a0bdc1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.0 CPython/3.9.7
|
