Faster R-CNN

Open weights Microsoft Research June 2015

No estimate

No hardware requirements for this model

This model's weights are open, but no parameter count has been published for it. Every memory and speed figure starts from that number, so we would rather show nothing than a fabricated estimate.

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 Research
Organisation type
Industry
Country
United States of America
Published
4 June 2015
Authors
S Ren, K He, R Girshick, J 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
102,400,000 tokens

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights
Open — downloadable
Model access
Open weights (unrestricted)
Training code
Open source

MIT license for repo: https://github.com/ShaoqingRen/faster_rcnn contains weights and training scripts

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
Unknown
Citations
72,570

Sources

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

Reference
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Last updated
25 May 2026

What the numbers mean

Where it came from

Faster R-CNN was published by Microsoft Research, in United States of America, in June 2015. It comes out of industry.

It works in Vision, and is recorded as doing object detection.

The weights are published, so it can be downloaded and run on your own hardware indefinitely, offline, with no account attached.

What went into building it

The training set ran to roughly 102,400,000 tokens.

The reason it appears in this catalogue at all is highly cited.

Answers

Faster R-CNN — common questions

01

Is Faster R-CNN open source?

Its weights are published, so Faster R-CNN can be downloaded and run on your own hardware. Note that open weights is not the same as open source in the full sense — it says nothing about the training data, the training code, or the commercial terms attached.

02

How many parameters does Faster R-CNN have?

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

03

Who created Faster R-CNN?

Faster R-CNN was published by Microsoft Research, based in United States of America, categorised as industry.

04

When was Faster R-CNN released?

Faster R-CNN was published in June 2015. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

05

What is Faster R-CNN used for?

Faster R-CNN works in Vision, and is recorded as handling object detection. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

06

Where can I download Faster R-CNN?

The weights for Faster R-CNN are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.

07

What GPU do I need to run Faster R-CNN?

We cannot say. Faster R-CNN has open weights, but no parameter count has been published for it, and every memory and speed calculation starts from that number. We would rather show nothing than a fabricated estimate.

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.