Repository for a reliable Deep Neural Network (DNN) model. DieHardNet stands for Die (integrated circuit) Hardened Neural Network
The directories are organized as follows:
- hg_noise_injector - A module to inject realistic errors in the training process
- eval_fault_injection_cfg - Configuration files for NVBITFI for fault injection
- pytorch_scripts - PyTorch scripts for training and inference for the used DNNs. For information read the README.
- With the Hans Gruber error injector
- Without the error injector
$ ./main.py ....
$ ./main.py ....
An example of running the inference with the pretrained hardened model
$ ./main.py ....
@INPROCEEDINGS{diehardnet,
author = {AUTHORS},
title = {TITLE},
booktitle = {PROCEEDINGS},
series = {EVENT},
year = {2022},
isbn = {ISBN},
}