chncwang/InsNet
InsNet Runs Instance-dependent Neural Networks with Padding-free Dynamic Batching.
This library helps natural language processing (NLP) researchers and engineers build complex neural network models, especially those with instance-dependent computation graphs like Tree-LSTMs or hierarchical Transformers. You input your NLP model design for a single instance, and it handles efficient, 'padding-free' batch processing, outputting a highly optimized and memory-efficient trained model. This is for advanced NLP practitioners who build custom neural network architectures.
No commits in the last 6 months.
Use this if you are developing advanced NLP models with instance-dependent computation graphs and want to avoid the complexities of manual batching and minimize memory usage.
Not ideal if you are using standard, pre-built NLP models or prefer deep learning libraries that require explicit tensor and padding management.
Stars
67
Forks
13
Language
C++
License
—
Category
Last pushed
Nov 20, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/chncwang/InsNet"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Ricardokevins/Kevinpro-NLP-demo
All NLP you Need Here. 目前包含15个NLP demo的pytorch实现（大量代码借鉴于其他开源项目，原先是自己玩的，后来干脆也开源出来）
spro/practical-pytorch
Go to https://github.com/pytorch/tutorials - this repo is deprecated and no longer maintained
allenai/allennlp-models
Officially supported AllenNLP models
graykode/nlp-tutorial
Natural Language Processing Tutorial for Deep Learning Researchers
apachecn/nlp-pytorch-zh
《Natural Language Processing with PyTorch》中文翻译