TA-CNN
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
- Chinese University of Hong Kong (CUHK)
- Organisation type
- Academia
- Country
- Hong Kong
- Published
- 29 November 2014
- Authors
- Yonglong Tian, Ping Luo, Xiaogang Wang, Xiaoou Tang
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision
- Task
- Object detection
- 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
- 706K
- Training data
- 45,000 tokens
Architecture details in Figure 4 Conv1: 3*7*7*32=4704 Conv2: 32*5*5*48=38400Conv3: 48*3*3*64=27648 Conv4: 64*3*3*96=55296 Fc5: 5*2*96*500=480000 Fc6: 500*200=100000 Total: 4704+38400+27648+55296+480000+100000=706048
Followed train test split detailed in Pedestrian Detection: An Evaluation of the State of the Art
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
- 1.1 × 10¹⁶ FLOP
- How it was established
- Hardware
Training time: 3h Assumed FP32 GPU FLOPs in 2014: 3.35e+12Assumed utilization: 0.3 Training FLOP: 3*60*60*0.3*3.35e12=10854000000000000=1.08e16
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Chips used
- 1
- Wall-clock time
- 3 hours
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
- SOTA improvement
- Record confidence
- Likely
"he proposed approach outperforms the state-of-the-art on the challenging Caltech and ETH datasets, where it reduces the miss rates of previous deep models by 17 and 5.5 percent, respectively. "
Sources
Where this record came from and when it was last checked.
- Reference
- Pedestrian Detection aided by Deep Learning Semantic Tasks
- Last updated
- 28 November 2025
What the numbers mean
About this model
TA-CNN was published by Chinese University of Hong Kong (CUHK), in Hong Kong, in November 2014. The organisation is categorised as academia.
It works in Vision, and is recorded as doing object detection.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
What went into building it
Training it took roughly 1.1 × 10¹⁶ FLOP of computation — a measure of what producing the model cost, not of how fast it answers.
It was trained on about 45,000 tokens of text.
The reason it appears in this catalogue at all is sOTA improvement.
Answers
TA-CNN — common questions
How many parameters does TA-CNN have?
TA-CNN has 706K parameters. Architecture details in Figure 4 Conv1: 3*7*7*32=4704 Conv2: 32*5*5*48=38400Conv3: 48*3*3*64=27648 Conv4: 64*3*3*96=55296 Fc5: 5*2*96*500=480000 Fc6: 500*200=100000 Total: 4704+38400+27648+55296+480000+100000=706048. 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.
Who created TA-CNN?
TA-CNN was published by Chinese University of Hong Kong (CUHK), based in Hong Kong, categorised as academia.
When was TA-CNN released?
TA-CNN was published in November 2014. 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 TA-CNN used for?
TA-CNN works in Vision, and is recorded as handling object detection. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
How much compute was used to train TA-CNN?
Around 1.1 × 10¹⁶ 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 TA-CNN?
None. TA-CNN 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 TA-CNN open source?
No. TA-CNN has not had its weights 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.