Good-DA-in-KD

A system for quickly generating training data with weak supervision

A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.

A large scale study of Knowledge Distillation.

Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.

Version control that works the way you think

Awesome Knowledge Distillation

TextAttack ? is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/

Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.

An Automatic Model Compression (AutoMC) framework for developing smaller and faster AI applications.

Collection of AWESOME vision-language models for vision tasks