ID	seresnet152d
LR	0.6
Epochs	100
Layers	152
Dropout	0.2
Crop Pct	0.94
Momentum	0.9
Batch Size	1024
Image Size	256
Interpolation	bicubic

ID	seresnet50
LR	0.6
Epochs	100
Layers	50
Dropout	0.2
Crop Pct	0.875
Momentum	0.9
Batch Size	1024
Image Size	224
Interpolation	bicubic

SE ResNet

rwightman / pytorch-image-models

Last updated on Feb 14, 2021

Parameters 67 Million

FLOPs 20 Billion

File Size 255.72 MB

Training Data ImageNet

Training Resources 8x NVIDIA Titan X GPUs

Training Time

Training Techniques	SGD with Momentum, Weight Decay, Label Smoothing
Architecture	1x1 Convolution, Squeeze-and-Excitation Block, Bottleneck Residual Block, Batch Normalization, Convolution, Global Average Pooling, Residual Block, Residual Connection, ReLU, Max Pooling, Softmax
ID	seresnet152d
LR	0.6
Epochs	100
Layers	152
Dropout	0.2
Crop Pct	0.94
Momentum	0.9
Batch Size	1024
Image Size	256
Interpolation	bicubic
SHOW MORE
SHOW LESS

Parameters 28 Million

FLOPs 5 Billion

File Size 107.40 MB

Training Data ImageNet

Training Resources 8x NVIDIA Titan X GPUs

Training Time

Training Techniques	SGD with Momentum, Weight Decay, Label Smoothing
Architecture	1x1 Convolution, Squeeze-and-Excitation Block, Bottleneck Residual Block, Batch Normalization, Convolution, Global Average Pooling, Residual Block, Residual Connection, ReLU, Max Pooling, Softmax
ID	seresnet50
LR	0.6
Epochs	100
Layers	50
Dropout	0.2
Crop Pct	0.875
Momentum	0.9
Batch Size	1024
Image Size	224
Interpolation	bicubic
SHOW MORE
SHOW LESS

README.md

Summary

SE ResNet is a variant of a ResNet that employs squeeze-and-excitation blocks to enable the network to perform dynamic channel-wise feature recalibration.

How do I load this model?

To load a pretrained model:

import timm
m = timm.create_model('seresnet50', pretrained=True)
m.eval()

Replace the model name with the variant you want to use, e.g. seresnet50. You can find the IDs in the model summaries at the top of this page.

How do I train this model?

You can follow the timm recipe scripts for training a new model afresh.

Citation

@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}
}

Results

Image Classification on ImageNet

Image Classification

BENCHMARK	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
ImageNet	seresnet152d	Top 1 Accuracy	83.74%	# 29
		Top 5 Accuracy	96.77%	# 29
ImageNet	seresnet50	Top 1 Accuracy	80.26%	# 91
		Top 5 Accuracy	95.07%	# 91