DCNN

Closed weights University of Maryland,Rutgers University 5M parameters August 2015

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
University of Maryland,Rutgers University
Organisation type
Academia,Academia
Country
United States of America
Published
7 August 2015
Authors
Jun-Cheng Chen, Vishal M. Patel, Rama Chellappa

What it does

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

Domain
Vision
Task
Face verification
Approach
Supervised

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.

Parameters
5M

Table 1

Training data
490,356 tokens

"The CASIA-WebFace dataset contains 494,414 face images of 10,575 subjects downloaded from the IMDB website. After removing the 27 overlapping subjects with the IJB-A dataset, there are 10548 subjects 1 and 490,356 face images."

Epochs
26

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
4.8 × 10¹⁷ FLOP

Total compute: 1535436288 forward pass flops *3* 1000000 iterations * 128 batch size = 589607534592000000 FLOP = 5.89607534592e17 FLOP Forward pass FLOPs based on CNN details in Table 1: Conv11: 2*3*3*32*100*100*1=5760000 Conv12: 2*3*3*64*100*100*32=368640000 Conv21: 2*3*3*64*50*50*64=184320000 Conv22: 2*3*3*64*50*50*128=368640000 Conv32: 2*3*3*128*25*25*96=138240000 Conv33: 2*3*3*96*25*25*192=207360000 Conv41: 2*3*3*192*13*13*128=74760192 Conv42: 2*3*3*128*13*13*256=99680256 Conv51: 2*3*3*256*…

How it was established
Operation counting,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 Tesla K40c
Chips used
1
Wall-clock time
216 hours (9 days)

"The DCNN model is trained for about 9 days using NVidia Tesla K40."

Power draw
286 W

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
Closed — provider access only
Model access
Unreleased
Training code
Unreleased

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
SOTA improvement

https://paperswithcode.com/sota/face-verification-on-ijb-a

Record confidence
Confident

Sources

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

Reference
Unconstrained Face Verification using Deep CNN Features
Last updated
28 November 2025

What the numbers mean

About this model

DCNN was published by University of Maryland,Rutgers University, in United States of America, in August 2015. The organisation is categorised as academia,Academia.

It works in Vision, and is recorded as doing face verification.

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

What went into building it

Training it took roughly 4.8 × 10¹⁷ FLOP of computation, on NVIDIA Tesla K40c — a measure of what producing the model cost, not of how fast it answers.

Around 490,356 tokens went into training it.

The reason it appears in this catalogue at all is sOTA improvement.

Answers

DCNN — common questions

01

When was DCNN released?

DCNN was published in August 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.

02

What is DCNN used for?

DCNN works in Vision, and is recorded as handling face verification. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

03

How much compute was used to train DCNN?

Around 4.8 × 10¹⁷ FLOP, on NVIDIA Tesla K40c. 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.

04

What GPU do I need to run DCNN?

None. DCNN 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.

05

Is DCNN open source?

No. DCNN has not had its weights published, so it exists only as a service controlled by its owner.

06

How many parameters does DCNN have?

DCNN has 5M parameters. Table 1. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.

07

Who created DCNN?

DCNN was published by University of Maryland,Rutgers University, based in United States of America, categorised as academia,Academia.

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.