SSD

Open weights December 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.

Published
8 December 2015
Authors
Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, Alexander C. Berg

What it does

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

Domain
Vision
Task
Object detection
Approach
Supervised
Base model
VGG16
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
2,300,000 tokens

Multiple datasets were used (PASCAL VOC, ILSVRC, COCO) but afaict COCO is the largest. Per this paper https://arxiv.org/abs/1703.06870v1, final paragraph before section 4.1, "As in previous work [3, 21], we train using the union of 80k train images and a 35k subset of val images (trainval35k), and report ablations on the remaining 5k subset of val images (minival)". So trainval35k is 80k + 35k = 115k

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 X

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)

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

Also listed in Denis Panjuta's List of 100+ AI Algorithms

Record confidence
Confident
Citations
39,468

Sources

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

Reference
SSD: Single Shot MultiBox Detector
Last updated
28 November 2025

What the numbers mean

What this model is

SSD was published by its authors, in December 2015.

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

It is derived from VGG16 rather than trained from scratch, which is the usual way a specialised model is produced.

The weights being open is what puts this page in the calculator rather than only in the catalogue: it is a model you can actually hold.

How it was trained

The training set ran to roughly 2,300,000 tokens.

Its inclusion criterion is highly cited.

Answers

SSD — common questions

01

What is SSD used for?

SSD 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.

02

Where can I download SSD?

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

03

What GPU do I need to run SSD?

We cannot say. SSD 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.

04

Is SSD open source?

Its weights are published, so SSD 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.

05

How many parameters does SSD have?

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

06

When was SSD released?

SSD was published in December 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.

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.