DL scaling Image

Closed weights Baidu 121M parameters December 2017

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
Baidu
Organisation type
Industry
Country
China
Published
1 December 2017
Authors
Joel Hestness, Sharan Narang, Newsha Ardalani, G. Diamos, Heewoo Jun, Hassan Kianinejad, Md. Mostofa Ali Patwary, Yang Yang, Yanqi Zhou

What it does

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

Domain
Vision
Task
Image classification
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
121M

We test models with parameter counts ranging from 89K to 121M.

Training data
tokens

We train and validate ResNets on various shard sizes of ImageNet, ranging from 1 image per class (0.08% of images) up to 800 images per class (62%). ImageNet has 1,000 different object classes as outputs

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

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
Training cost
Record confidence
Confident

Sources

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

Reference
Deep Learning Scaling is Predictable, Empirically
Last updated
28 November 2025

What the numbers mean

Background

DL scaling Image was published by Baidu, in China, in December 2017. It comes out of industry.

It works in Vision, and is recorded as doing image classification.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

How it was trained

Its inclusion criterion is training cost.

Answers

DL scaling Image — common questions

01

When was DL scaling Image released?

DL scaling Image was published in December 2017. 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 DL scaling Image used for?

DL scaling Image works in Vision, and is recorded as handling image classification. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

03

What GPU do I need to run DL scaling Image?

None. DL scaling Image 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.

04

Is DL scaling Image open source?

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

05

How many parameters does DL scaling Image have?

DL scaling Image has 121M parameters. We test models with parameter counts ranging from 89K to 121M. 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.

06

Who created DL scaling Image?

DL scaling Image was published by Baidu, based in China, categorised as industry.

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.