Refined Part Pooling
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
- Tsinghua University,University of Technology Sydney,University of Texas at San Antonio
- Organisation type
- Academia,Academia,Academia
- Country
- China, Australia, United States of America
- Published
- 9 January 2018
- Authors
- Yifan Sun, Liang Zheng, Yi Yang, Qi Tian, Shengjin Wang
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision
- Task
- Person retrieval
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
- 77,616 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
- 2.6 × 10¹⁶ FLOP
- How it was established
- Hardware
12150000000000*3600*2*0.3=2.6244e+16 FLOP
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 TITAN Xp
- Chips used
- 2
- Wall-clock time
- 1 hours
- Power draw
- 1.0 kW
"With two NVIDIA TITAN XP GPUs and Pytorch as the platform, training an IDE model and a standard PCB on Market-1501 (12,936 training images) consumes about 40 and 50 minutes, respectively"
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
- 2,377
Sources
Where this record came from and when it was last checked.
- Reference
- Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)
- Last updated
- 25 May 2026
What the numbers mean
Where it came from
Refined Part Pooling was published by Tsinghua University,University of Technology Sydney,University of Texas at San Antonio, in China, in January 2018. It comes out of academia,Academia,Academia.
It works in Vision, and is recorded as doing person retrieval.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
How it was trained
Producing it required around 2.6 × 10¹⁶ FLOP of arithmetic, on NVIDIA TITAN Xp, which is a statement about the training budget rather than about inference.
It was trained on about 77,616 tokens of text.
Answers
Refined Part Pooling — common questions
How much compute was used to train Refined Part Pooling?
Around 2.6 × 10¹⁶ FLOP, on NVIDIA TITAN Xp. 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 Refined Part Pooling?
None. Refined Part Pooling 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.
Is Refined Part Pooling open source?
The licensing for Refined Part Pooling was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
How many parameters does Refined Part Pooling have?
No parameter count has been published for Refined Part Pooling, which is why no memory or speed figure appears on this page.
Who created Refined Part Pooling?
Refined Part Pooling was published by Tsinghua University,University of Technology Sydney,University of Texas at San Antonio, based in China, categorised as academia,Academia,Academia.
When was Refined Part Pooling released?
Refined Part Pooling was published in January 2018. 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 Refined Part Pooling used for?
Refined Part Pooling works in Vision, and is recorded as handling person retrieval. These are the areas it was designed around; they describe intent rather than a hard boundary.
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.