R-FCN
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
- Tsinghua University,Microsoft Research
- Organisation type
- Academia,Industry
- Country
- China, United States of America
- Published
- 21 June 2016
- Authors
- Jifeng Dai, Y. Li, Kaiming He, and Jian Sun
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision
- Task
- Object detection
- 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
- 10,624,000 tokens
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
- 7.2 × 10¹⁷ FLOP
- How it was established
- Hardware
1,464 images in 2012 VOC (https://paperswithcode.com/dataset/pascal-voc)/ 9,963 images in 2007 VOC (https://www.tensorflow.org/datasets/catalog/voc) 83K training images in MS COCO (https://paperswithcode.com/dataset/coco) They used a Nvidia K40 GPU and report training time/image in seconds (table 3) Assumed a 0.33 util rate Section 4.2 (MS COCO): "Next we evaluate on the MS COCO dataset [ 13 ] that has 80 object categories. Our experiments involve the 80k train set, 40k val set, and 20k tes…
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
- Highly cited
- Record confidence
- Confident
- Citations
- 6,003
Sources
Where this record came from and when it was last checked.
- Reference
- R-fcn: Object detection via region-based fully convolutional networks.
- Last updated
- 25 May 2026
What the numbers mean
Where it came from
R-FCN was published by Tsinghua University,Microsoft Research, in China, in June 2016. The organisation is categorised as academia,Industry.
It works in Vision, and is recorded as doing object detection.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
What went into building it
Training it took roughly 7.2 × 10¹⁷ FLOP of computation — a measure of what producing the model cost, not of how fast it answers.
It was trained on about 10,624,000 tokens of text.
The reason it appears in this catalogue at all is highly cited.
Answers
R-FCN — common questions
How much compute was used to train R-FCN?
Around 7.2 × 10¹⁷ FLOP. 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.
What GPU do I need to run R-FCN?
None. R-FCN 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.
Is R-FCN open source?
The licensing for R-FCN was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
How many parameters does R-FCN have?
No parameter count has been published for R-FCN, which is why no memory or speed figure appears on this page.
Who created R-FCN?
R-FCN was published by Tsinghua University,Microsoft Research, based in China, categorised as academia,Industry.
When was R-FCN released?
R-FCN was published in June 2016. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
What is R-FCN used for?
R-FCN works in Vision, and is recorded as handling object detection. These are the areas it was designed around; they describe intent rather than a hard boundary.
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.