ganler / nnsmith

Automatic DNN generation for fuzzing and more.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

logo

NNSmith

🌟NNSmith🌟 is a random DNN generator and a fuzzing infrastructure, primarily designed for automatically validating deep-learning frameworks and compilers.

Support Table

Models tvm pt2 torchjit tensorrt onnxruntime xla tflite
ONNX βœ… βœ… βœ…
PyTorch βœ…πŸ“ˆ βœ…πŸ“ˆ
TensorFlow βœ… βœ…

βœ…: Supported; πŸ“ˆ: Supports gradient check;

Quick Start

Install latest code (GitHub HEAD):

pip install pip --upgrade
pip install "nnsmith[torch,onnx] @ git+https://github.com/ise-uiuc/nnsmith@main" --upgrade
# [optional] add more front- and back-ends such as [tensorflow] and [tvm,onnxruntime,...] in "[...]"
Install latest stable release [click]
pip install "nnsmith[torch,onnx]" --upgrade
Install latest pre-release [click]
pip install "nnsmith[torch,onnx]" --upgrade --pre
Setting up graphviz for debugging [click]

Graphviz provides dot for visualizing graphs in nice pictures. But it needs to be installed via the following methods:

sudo apt-get install graphviz graphviz-dev      # Linux
brew install graphviz                           # MacOS
conda install --channel conda-forge pygraphviz  # Conda
choco install graphviz                          # Windows

pip install pygraphviz  # Final step.

Also see pygraphviz install guidance.

# Generate a random model in "nnsmith_outputs/*"
nnsmith.model_gen model.type=onnx debug.viz=true

Learning More

Papers

πŸ“œ NeuRI: Diversifying DNN Generation via Inductive Rule Inference [click :: citation]
@article{liu2023neuri,
  title = {NeuRI: Diversifying DNN Generation via Inductive Rule Inference},
  author = {Liu, Jiawei and Peng, Jinjun and Wang, Yuyao and Zhang, Lingming},
  journal = {arXiv preprint arXiv:2302.02261},
  year = {2023},
}

πŸ“œ NNSmith: Generating Diverse and Valid Test Cases for Deep Learning Compilers [click :: citation]
@inproceedings{liu2023nnsmith,
  title={Nnsmith: Generating diverse and valid test cases for deep learning compilers},
  author={Liu, Jiawei and Lin, Jinkun and Ruffy, Fabian and Tan, Cheng and Li, Jinyang and Panda, Aurojit and Zhang, Lingming},
  booktitle={Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2},
  pages={530--543},
  year={2023}
}

About

Automatic DNN generation for fuzzing and more.

License:Apache License 2.0


Languages

Language:Python 99.5%Language:Shell 0.5%