ESE_VoVNet39b

Quantized ESE_VoVNet39b model that could be supported by AMD Ryzen AI.

Model description

VoVNet was first introduced in the paper An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection. Pretrained on ImageNet-1k in timm by Ross Wightman using RandAugment RA recipe.

The model implementation is from timm.

How to use

Installation

Follow Ryzen AI Installation to prepare the environment for Ryzen AI. Run the following script to install pre-requisites for this model.

pip install -r requirements.txt 

Data Preparation

Follow ImageNet to prepare dataset.

Model Evaluation

python eval_onnx.py --onnx_model ese_vovnet39b_int.onnx --ipu --provider_config Path\To\vaip_config.json --data_dir /Path/To/Your/Dataset

Performance

Metric	Accuracy on IPU
Top1/Top5	78.96% / 94.53%

@misc{rw2019timm,
  author = {Ross Wightman},
  title = {PyTorch Image Models},
  year = {2019},
  publisher = {GitHub},
  journal = {GitHub repository},
  doi = {10.5281/zenodo.4414861},
  howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}

@inproceedings{lee2019energy,
  title = {An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection},
  author = {Lee, Youngwan and Hwang, Joong-won and Lee, Sangrok and Bae, Yuseok and Park, Jongyoul},
  booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops},
  year = {2019}
}