SPPNet
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
- How it was established
- Hardware
"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
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)
- Compute cost
- $52
"All networks in this paper can be trained on a single GeForce GTX Titan GPU (6 GB memory) within two to four weeks."
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 the country recorded as United States of America, during June 2014. The category the publisher falls under is industry,Academia,Academia.
It works in the domain of Vision, and is recorded as performing the task of 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 a computation budget of roughly 3.4 × 10¹⁸ FLOP, on hardware recorded as NVIDIA GeForce GTX TITAN. That figure measures what producing the model cost, and has no bearing on how fast it answers.
The training set ran to roughly 1,280,000 tokens of text.
Its inclusion criterion: highly cited.
Answers
SPPNet — common questions
SPPNet— who created it?
It was published by Microsoft,Xi’an Jiaotong University,University of Science and Technology of China (USTC), based in United States of America, an organisation categorised as industry,Academia,Academia.
SPPNet— when was it released?
It 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.
SPPNet— what is it used for?
It works in the domain of Vision, and is recorded as handling the task of image classification. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
SPPNet— how much compute was used to train it?
Training consumed around 3.4 × 10¹⁸ FLOP, on hardware recorded as 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.
SPPNet— what GPU do I need to run it?
None. This 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.
SPPNet— is it open source?
The licensing was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
SPPNet— how many parameters does it have?
No parameter count has been published for it, which is why no memory or speed figure appears on this page.
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.