metadata

license: apache-2.0
datasets:
  - imagenet-1k
metrics:
  - accuracy
tags:
  - RyzenAI
  - vision
  - classification
  - pytorch
  - timm

MNASNet_b1

Quantized MNASNet_b1 model that could be supported by AMD Ryzen AI.

Model description

MNASNet was first introduced in the paper MnasNet: Platform-Aware Neural Architecture Search for Mobile.

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 mnasnet_b1_int.onnx --ipu --provider_config Path\To\vaip_config.json --data_dir /Path/To/Your/Dataset

Performance

Metric	Accuracy on IPU
Top1/Top5	73.51% / 91.56%

@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{tan2019mnasnet,
  title={Mnasnet: Platform-aware neural architecture search for mobile},
  author={Tan, Mingxing and Chen, Bo and Pang, Ruoming and Vasudevan, Vijay and Sandler, Mark and Howard, Andrew and Le, Quoc V},
  booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
  pages={2820--2828},
  year={2019}
}