Project AURIONAI Use-Cases Research & Innovation
Tsinghua University
vision

RepVGG

VGG-style plain CNN that is trained with branches and re-parameterised into a single path for fast inference.

Tsinghua UniversityTsinghua UniversityChinaMegviiMegviiChina
Figure from the RepVGG paper: Structural re-parameterization of a RepVGG block.
Levelmodel
Classvision
Parameters9.13M
Contextnot in the notes
Released11 Jan 2021
Opennessopen weights permissive
Runs onCPU server
Statusactive

R&D Topics

Image classification backbone architectures (CNN and vision transformer)produced by

Identity

Developer
Tsinghua University, Megvii
Family
not in the notes
Released
11 Jan 2021 sourcesannouncement page
Weights published
23 Aug 2023
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
9.13M sources
Active parameters
–
Checkpoint parameters
–
Note
RepVGG A0 to B3.
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
open weights permissive
Licence
MIT License sources
Access routes
open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
CPU server
Footprint
Edge or toolkit builds listed in: OpenVINO.
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.

Sources

  1. arxiv.org/abs/2101.03697 https://arxiv.org/abs/2101.03697
  2. huggingface.co/timm/repvgg_a0.rvgg_in1k https://huggingface.co/timm/repvgg_a0.rvgg_in1k
  3. github.com/openvinotoolkit/open_model_zoo/tree/master/mo... https://github.com/openvinotoolkit/open_model_zoo/tree/master/models/public/repvgg-a0
  4. huggingface.co/api/models?pipeline_tag=image-classification&... https://huggingface.co/api/models?pipeline_tag=image-classification&sort=downloads&limit=50
  5. github.com/open-mmlab/mmpretrain/tree/main/configs/repvgg https://github.com/open-mmlab/mmpretrain/tree/main/configs/repvgg
  6. github.com/huggingface/pytorch-image-models/blob/main/RE... https://github.com/huggingface/pytorch-image-models/blob/main/README.md
  7. github.com/onnx/models/tree/main/Computer_Vision/repvgg_... https://github.com/onnx/models/tree/main/Computer_Vision/repvgg_a2_Opset16_timm
  8. arxiv.org/html/2101.03697 https://arxiv.org/html/2101.03697

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "RepVGG", https://aurion.semai.id/models/repvgg/, records of October 2026.