SPPNet

Closed weights Microsoft,Xi’an Jiaotong University,University of Science and Technology of China (USTC) June 2014

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
Microsoft,Xi’an Jiaotong University,University of Science and Technology of China (USTC)
Organisation type
Industry,Academia,Academia
Country
United States of America, China
Published
18 June 2014
Authors
Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun

What it does

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

Domain
Vision
Task
Image classification
Numerical format
FP32

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.

Training data
1,280,000 tokens

Section 3.1: "We train the networks on the 1000-category training set of ImageNet 2012."

Training compute

The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.

Training compute
3.4 × 10¹⁸ FLOP

"All networks in this paper can be trained on a single GeForce GTX Titan GPU (6 GB memory) within two to four weeks." 4.7e12 FLOP/s * 4* 7*24*60*60 seconds * 0.3 utilisation

How it was established
Hardware

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 GeForce GTX TITAN
Wall-clock time
672 hours (28 days)

"All networks in this paper can be trained on a single GeForce GTX Titan GPU (6 GB memory) within two to four weeks."

Compute cost
$52

How it is classified

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

Frontier model
Yes
Why it is tracked
Highly cited
Record confidence
Confident
Citations
12,524

Sources

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

Reference
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
Last updated
25 May 2026

What the numbers mean

Background

SPPNet was published by Microsoft,Xi’an Jiaotong University,University of Science and Technology of China (USTC), in United States of America, in June 2014. industry,Academia,Academia is the category the publisher falls under.

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

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

Training and provenance

Training it took roughly 3.4 × 10¹⁸ FLOP of computation, on NVIDIA GeForce GTX TITAN — a measure of what producing the model cost, not of how fast it answers.

The training set ran to roughly 1,280,000 tokens.

Its inclusion criterion is highly cited.

Answers

SPPNet — common questions

01

Who created SPPNet?

SPPNet was published by Microsoft,Xi’an Jiaotong University,University of Science and Technology of China (USTC), based in United States of America, categorised as industry,Academia,Academia.

02

When was SPPNet released?

SPPNet was published in June 2014. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

03

What is SPPNet used for?

SPPNet 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.

04

How much compute was used to train SPPNet?

Around 3.4 × 10¹⁸ FLOP, on NVIDIA GeForce GTX TITAN. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.

05

What GPU do I need to run SPPNet?

None. SPPNet 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 SPPNet open source?

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

07

How many parameters does SPPNet have?

No parameter count has been published for SPPNet, which is why no memory or speed figure appears on this page.

Source

Original publication

Record last updated 25 May 2026

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.