Training Techniques | SGD with Momentum, Weight Decay, Label Smoothing |
---|---|
Architecture | Convolution, Dense Connections, Global Average Pooling, Max Pooling, Softmax, Squeeze-and-Excitation Block |
ID | legacy_senet154 |
SHOW MORE |
A SENet is a convolutional neural network architecture that employs squeeze-and-excitation blocks to enable the network to perform dynamic channel-wise feature recalibration.
The weights from this model were ported from Gluon.
To load a pretrained model:
import timm
m = timm.create_model('gluon_senet154', pretrained=True)
m.eval()
Replace the model name with the variant you want to use, e.g. gluon_senet154
. 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{hu2019squeezeandexcitation,
title={Squeeze-and-Excitation Networks},
author={Jie Hu and Li Shen and Samuel Albanie and Gang Sun and Enhua Wu},
year={2019},
eprint={1709.01507},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
BENCHMARK | MODEL | METRIC NAME | METRIC VALUE | GLOBAL RANK |
---|---|---|---|---|
ImageNet | legacy_senet154 | Top 1 Accuracy | 81.33% | # 62 |
Top 5 Accuracy | 95.51% | # 62 |