vision
SE-ResNet and SE-ResNeXt (Squeeze-and-Excitation)
Image classifiers that add Squeeze-and-Excitation channel attention blocks to ResNet and ResNeXt; SENet won ImageNet 2017.
Levelmodel
Classvision
Parametersnot in the notes
Contextnot in the notes
Released5 Sep 2017
Opennessunknown
Runs onnot in the notes
Statusactive
Identity
- Developer
- Momenta, University of Oxford
- Family
- not in the notes
- Released
- 5 Sep 2017 sourcesannouncement page
- Weights published
- –
- Record checked
- 12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.
Architecture and Size
- Architecture
- CNN
- Total parameters
- – sources
- Active parameters
- –
- Checkpoint parameters
- –
- Note
- SE-ResNet, SE-ResNeXt and SENet-154 (timm, NVIDIA Deep Learning Examples).
- Context length
- not in the notes
- Input
- image
- Output
- labels and boxes
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).
Openness and Access
- Openness
- unknown
- Licence
- not in the notes sources
- Access routes
- open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.
Deployment
- Runs on
- not in the notes
- Footprint
- not in the notes
- Runtimes
- not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.
Indonesia
- Indonesian support
- not stated
- Regional languages
- not in the notes
- Jakarta hosting
- unknown
- Languages
- not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.
Benchmark Results
The notes record no benchmark result for this model.
Lineage
The notes record no lineage for this model.
Industry Use Cases
No industry use case links this model.
Links
ModelSE-ResNet and SE-ResNeXt (Squeeze-and-Excitation)Momenta, vision
SE-ResNet and SE-ResNeXt (Squeeze-and-Excitation)Momenta, visionUse Casesnone recorded
Who Runs Itnone recorded
Sources
- arxiv.org/abs/1709.01507 https://arxiv.org/abs/1709.01507
- pytorch.org/hub/nvidia_deeplearningexamples_se-resnext https://pytorch.org/hub/nvidia_deeplearningexamples_se-resnext
- raw.githubusercontent.com/pytorch/hub/master/nvidia_deeplearningexample... https://raw.githubusercontent.com/pytorch/hub/master/nvidia_deeplearningexamples_se-resnext.md
- github.com/NVIDIA/DeepLearningExamples/tree/master/PyTor... https://github.com/NVIDIA/DeepLearningExamples/tree/master/PyTorch/Classification/ConvNets/se-resnext101-32x4d
- github.com/open-mmlab/mmpretrain/tree/main/configs/seres... https://github.com/open-mmlab/mmpretrain/tree/main/configs/seresnet
- github.com/huggingface/pytorch-image-models/blob/main/RE... https://github.com/huggingface/pytorch-image-models/blob/main/README.md
- github.com/onnx/models/tree/main/Computer_Vision/gluon_s... https://github.com/onnx/models/tree/main/Computer_Vision/gluon_senet154_Opset16_timm
- arxiv.org/html/1709.01507 https://arxiv.org/html/1709.01507
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "SE-ResNet and SE-ResNeXt (Squeeze-and-Excitation)", https://aurion.semai.id/models/se-resnet/, records of October 2026.