ResNet-152 (ImageNet)

Closed weights Microsoft 60.2M parameters December 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
Microsoft
Organisation type
Industry
Country
United States of America
Published
10 December 2015
Authors
Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun

What it does

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

Domain
Vision
Task
Image classification
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.

Parameters
60.2M

Taken from https://arxiv.org/abs/1605.07146

Training data
1,280,000 tokens

"We evaluate our method on the ImageNet 2012 classification dataset [36] that consists of 1000 classes. The models are trained on the 1.28 million training images"

Epochs
120
Batch size
256

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
1 × 10¹⁹ FLOP

11.3 *10^9 mult-adds per forward pass (Table 1) 2 FLOPS/ mult-add 3 for forward & backward pass 1.2 * 10^6 examples in dataset 128 epochs -> 1.041408 × 10^19 FLOP Authors of "AI and Memory Wall" (https://github.com/amirgholami/ai_and_memory_wall) estimated model's training compute as 11,000 PFLOP = 1.1*10^19 FLOP

How it was established
Operation counting,Third-party estimation

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
228,517

Sources

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

Reference
Deep Residual Learning for Image Recognition
Last updated
25 May 2026

What the numbers mean

Background

ResNet-152 (ImageNet) was published by Microsoft, in United States of America, in December 2015. It comes out of industry.

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

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

What went into building it

Producing it required around 1 × 10¹⁹ FLOP of arithmetic, which is a statement about the training budget rather than about inference.

Around 1,280,000 tokens went into training it.

It is tracked in the underlying dataset for one reason in particular: highly cited.

Answers

ResNet-152 (ImageNet) — common questions

01

When was ResNet-152 (ImageNet) released?

ResNet-152 (ImageNet) 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.

02

What is ResNet-152 (ImageNet) used for?

ResNet-152 (ImageNet) works in Vision, and is recorded as handling image classification. These are the areas it was designed around; they describe intent rather than a hard boundary.

03

How much compute was used to train ResNet-152 (ImageNet)?

Around 1 × 10¹⁹ 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.

04

What GPU do I need to run ResNet-152 (ImageNet)?

None. ResNet-152 (ImageNet) 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 ResNet-152 (ImageNet) open source?

The licensing for ResNet-152 (ImageNet) was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

06

How many parameters does ResNet-152 (ImageNet) have?

ResNet-152 (ImageNet) has 60.2M parameters. Taken from https://arxiv.org/abs/1605.07146. 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 ResNet-152 (ImageNet)?

ResNet-152 (ImageNet) was published by Microsoft, based in United States of America, categorised as industry.

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.