vision
AlexNet
Deep convolutional image classifier by Krizhevsky, Sutskever and Hinton (NeurIPS 2012) that won ImageNet 2012; still shipped as a baseline in TorchVision, ONNX and cloud model zoos.
Levelmodel
Classvision
Parametersnot in the notes
Contextnot in the notes
Released2012
Opennessunknown
Runs onnot in the notes
Statusactive
Identity
- Developer
- not in the notes
- Family
- not in the notes
- Released
- 2012 sourcesinferred from 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
- Single-GPU variant described in arXiv 1404.5997 ("One weird trick"); TorchVision ships the ImageNet weights.
- 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, cloud marketplace
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
Developersnone recorded
ModelAlexNetvision
Use Casesnone recorded
Who Runs Itnone recorded
Sources
- arxiv.org/abs/1404.5997 https://arxiv.org/abs/1404.5997
- papers.nips.cc/paper/2012/hash/c399862d3b9d6b76c8436e924a68c... https://papers.nips.cc/paper/2012/hash/c399862d3b9d6b76c8436e924a68c45b-Abstract.html
- jumpstart-cache-prod-us-west-2.s3.us-west-2.amazonaws.com/models_manifest.json https://jumpstart-cache-prod-us-west-2.s3.us-west-2.amazonaws.com/models_manifest.json
- pytorch.org/hub/pytorch_vision_alexnet https://pytorch.org/hub/pytorch_vision_alexnet
- raw.githubusercontent.com/pytorch/hub/master/pytorch_vision_alexnet.md https://raw.githubusercontent.com/pytorch/hub/master/pytorch_vision_alexnet.md
- github.com/pytorch/vision/blob/main/torchvision/models/a... https://github.com/pytorch/vision/blob/main/torchvision/models/alexnet.py
- pytorch.org/vision/stable/models/alexnet.html https://pytorch.org/vision/stable/models/alexnet.html
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "AlexNet", https://aurion.semai.id/models/alexnet/, records of October 2026.