OR-WideResNet

Closed weights Duke University,University of Chinese Academy of Sciences 18.2M parameters January 2017

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
Duke University,University of Chinese Academy of Sciences
Organisation type
Academia,Academia
Country
United States of America, China
Published
7 January 2017
Authors
Yanzhao Zhou, Qixiang Ye, Qiang Qiu and Jianbin Jiao

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Vision
Task
Image classification

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Parameters
18.2M

18.2M for largest OR-WideResNet model.

Training data
50,000 tokens

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Training hardware
NVIDIA Tesla K80

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Why it is tracked
SOTA improvement

"In Sec. 4.3, we upgrade the VGG [38], ResNet [18], and the WideResNet [45] to ORNs, and train them on CIFAR10 and CIFAR100 [22], showing the state-of-the-art performance on the natural image classification task."

Record confidence
Confident
Citations
285

Sources

Where this record came from and when it was last checked.

Reference
Oriented Response Networks
Last updated
28 November 2025

What the numbers mean

Where it came from

OR-WideResNet was published by Duke University,University of Chinese Academy of Sciences, in United States of America, in January 2017. It comes out of academia,Academia.

It works in Vision, and is recorded as doing image classification.

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

Training and provenance

The training set ran to roughly 50,000 tokens.

The reason it appears in this catalogue at all is sOTA improvement.

Answers

OR-WideResNet — common questions

01

How many parameters does OR-WideResNet have?

OR-WideResNet has 18.2M parameters. 18.2M for largest OR-WideResNet model. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.

02

Who created OR-WideResNet?

OR-WideResNet was published by Duke University,University of Chinese Academy of Sciences, based in United States of America, categorised as academia,Academia.

03

When was OR-WideResNet released?

OR-WideResNet was published in January 2017. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

04

What is OR-WideResNet used for?

OR-WideResNet works in Vision, and is recorded as handling image classification. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

05

What GPU do I need to run OR-WideResNet?

None. OR-WideResNet is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

06

Is OR-WideResNet open source?

The licensing for OR-WideResNet was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

Source

Original publication

Record last updated 28 November 2025

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.