| Architecture | Depthwise Separable Convolution, Batch Normalization, ReLU, Average Pooling, Convolution, Dropout |
|---|---|
| ID | spnasnet_100 |
| SHOW MORE |
Single-Path NAS is a novel differentiable NAS method for designing hardware-efficient ConvNets in less than 4 hours.
To load a pretrained model:
import timm
m = timm.create_model('spnasnet_100', pretrained=True)
m.eval()
Replace the model name with the variant you want to use, e.g. spnasnet_100. You can find the IDs in the model summaries at the top of this page.
You can follow the timm recipe scripts for training a new model afresh.
@misc{stamoulis2019singlepath,
title={Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours},
author={Dimitrios Stamoulis and Ruizhou Ding and Di Wang and Dimitrios Lymberopoulos and Bodhi Priyantha and Jie Liu and Diana Marculescu},
year={2019},
eprint={1904.02877},
archivePrefix={arXiv},
primaryClass={cs.LG}
}
Image Classification
| BENCHMARK | MODEL | METRIC NAME | METRIC VALUE | GLOBAL RANK |
|---|---|---|---|---|
| ImageNet | spnasnet_100 | Top 1 Accuracy | 74.08% | # 242 |
| Top 5 Accuracy | 91.82% | # 242 |
