ResNet-200
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 Research Asia
- Organisation type
- Industry
- Country
- China
- Published
- 17 September 2016
- 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
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
- 1,281,167 tokens
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
- 3 × 10¹⁹ FLOP
- How it was established
- Hardware
"ResNet-200 takes about 3 weeks to train on 8 GPUs". didn't specify which GPU upd: common GPU performance for 2016 is 6.83E+12 FLOPs/s (https://epoch.ai/blog/estimating-training-compute#forward-pass-compute-and-parameter-counts-of-common-layers) then 6.83E+12*3*7*24*3600*8*0.3=2.9741645e+19 (Speculative)
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Wall-clock time
- 500 hours (20.8 days)
"about 3 weeks"
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
- Open (non-commercial)
https://github.com/KaimingHe/resnet-1k-layers no definite license
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
- Speculative
- Citations
- 10,822
Sources
Where this record came from and when it was last checked.
- Reference
- Identity Mappings in Deep Residual Networks
- Last updated
- 1 January 2026
What the numbers mean
Where it came from
ResNet-200 was published by Microsoft Research Asia, in China, in September 2016. 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.
Training and provenance
Training it took roughly 3 × 10¹⁹ FLOP of computation — a measure of what producing the model cost, not of how fast it answers.
It was trained on about 1,281,167 tokens of text.
Its inclusion criterion is highly cited.
Answers
ResNet-200 — common questions
Is ResNet-200 open source?
No. ResNet-200 has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does ResNet-200 have?
No parameter count has been published for ResNet-200, which is why no memory or speed figure appears on this page.
Who created ResNet-200?
ResNet-200 was published by Microsoft Research Asia, based in China, categorised as industry.
When was ResNet-200 released?
ResNet-200 was published in September 2016. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
What is ResNet-200 used for?
ResNet-200 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.
How much compute was used to train ResNet-200?
Around 3 × 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.
What GPU do I need to run ResNet-200?
None. ResNet-200 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.
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.