isspek / anomaly-adapters

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

AnomalyAdapters

Parameter-efficient Multi-Anomaly Task Detection. This work is under review.

Testing

Latest test are done with adapter-transformers@V2.2.0a1

Follow the installation at:

https://github.com/Adapter-Hub/adapter-transformers#installation

To use mixed precision:

CUDA and C++ extensions via

git clone https://github.com/NVIDIA/apex
cd apex
pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./

Apex also supports a Python-only build (required with Pytorch 0.4) via

pip install -v --disable-pip-version-check --no-cache-dir ./

Special Thanks to

Huggingface, adapter-transformers and Allennlp repositories

Logo

Just for fun, I created my version :)

About

License:MIT License


Languages

Language:Jupyter Notebook 66.6%Language:Python 33.4%