Architecture | Convolution, Max Pooling, One-Shot Aggregation, Batch Normalization, ReLU |
---|---|
ID | ese_vovnet19b_dw |
SHOW MORE |
Architecture | Convolution, Max Pooling, One-Shot Aggregation, Batch Normalization, ReLU |
---|---|
ID | ese_vovnet39b |
SHOW MORE |
VoVNet is a convolutional neural network that seeks to make DenseNet more efficient by concatenating all features only once in the last feature map, which makes input size constant and enables enlarging new output channel.
Read about one-shot aggregation here.
To load a pretrained model:
import timm
m = timm.create_model('ese_vovnet39b', pretrained=True)
m.eval()
Replace the model name with the variant you want to use, e.g. ese_vovnet39b
. 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{lee2019energy,
title={An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection},
author={Youngwan Lee and Joong-won Hwang and Sangrok Lee and Yuseok Bae and Jongyoul Park},
year={2019},
eprint={1904.09730},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
BENCHMARK | MODEL | METRIC NAME | METRIC VALUE | GLOBAL RANK |
---|---|---|---|---|
ImageNet | ese_vovnet39b | Top 1 Accuracy | 79.31% | # 123 |
Top 5 Accuracy | 94.72% | # 123 | ||
ImageNet | ese_vovnet19b_dw | Top 1 Accuracy | 76.82% | # 202 |
Top 5 Accuracy | 93.28% | # 202 |