ResNet-152 + ObjectNet
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
- Massachusetts Institute of Technology (MIT)
- Organisation type
- Academia
- Country
- United States of America
- Published
- 6 September 2019
- Authors
- Andrei Barbu, David Mayo, Julian Alverio, William Luo, Christopher Wang, Dan Gutfre- und, Josh Tenenbaum, and Boris Katz
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision
- Task
- Object recognition
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
- 38M
- Training data
- 50,000 tokens
In total, 95,824 images were collected from 5,982 workers out of which 50,000 images were retained after validation and included in the dataset
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
- 1.9 × 10¹⁹ FLOP
- How it was established
- Hardware
3-5 days of training (say, 4.5), 50 teraFLOP/second at 50% utilization rate (reported) = 1.94E19
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.
- Record confidence
- Confident
- Citations
- 2,393
Sources
Where this record came from and when it was last checked.
- Reference
- Objectnet: A large-scale bias-controlled dataset for pushing the limits of object recognition models
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
ResNet-152 + ObjectNet was published by Massachusetts Institute of Technology (MIT), in the country recorded as United States of America, during September 2019. The category the publisher falls under is academia.
It works in the domain of Vision, and is recorded as performing the task of object recognition.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
Training and provenance
The training run consumed about 1.9 × 10¹⁹ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.
The training set ran to roughly 50,000 tokens of text.
Answers
ResNet-152 + ObjectNet — common questions
ResNet-152 + ObjectNet— how many parameters does it have?
It has a parameter count of 38M. 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.
ResNet-152 + ObjectNet— who created it?
It was published by Massachusetts Institute of Technology (MIT), based in United States of America, an organisation categorised as academia.
ResNet-152 + ObjectNet— when was it released?
It was published in September 2019. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
ResNet-152 + ObjectNet— what is it used for?
It works in the domain of Vision, and is recorded as handling the task of object recognition. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.
ResNet-152 + ObjectNet— how much compute was used to train it?
Training consumed around 1.9 × 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.
ResNet-152 + ObjectNet— what GPU do I need to run it?
None. This 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.
ResNet-152 + ObjectNet— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
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.