Hybrid CNN/SVM Object Categorizer
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
- Courant Institute of Mathematical Sciences
- Organisation type
- Academia
- Country
- United States of America
- Published
- 17 June 2006
- Authors
- Fu Jie Huang, Yann LeCun
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision
- Task
- Object recognition, 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.
- Parameters
- 3.6M
- Training data
- 291,600 tokens
- Epochs
- 14
For the CNN: "In this case, the whole network has a total of 90,857 trainable parameters." For the SVM: there are 6 binary SVM models trained support vectors = 0.02x291600 dimension = 100 parameters = (0.02x291600)x100x6=3499200 Total = 3590057
"Each object is captured by a camera pair with 162 different views (9 elevations from 30◦ to 70◦ every 5◦, 18 azimuths sampled every 20◦ along the horizontal viewing circle) and under 6 different illuminations." "To generate the training set, each image was perturbed with 10 different configurations of the above parameters, which makes up 291,600 image pairs of size 108×108. The testing set has 2 drawings of perturbations, and have 58,320 pairs"
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
- 9.8 × 10¹³ FLOP
- How it was established
- Operation counting
(291,600)*(8e6)*3*14 "A full propagation of one data sample through the network requires about 4 million multiply-add operations" = 2*4e6 FLOPs "The training and testing features are extracted with the convolutional net trained after 14 passes" "The experiments here are run on a single CPU (AMD Opteron at 2GHz) with 4GB of memory"
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
- 52 hours
Train time = (5880+330 min*GHz) * (1/(CPU=2GHz) * (1 hr/60 min) = 51.75 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.
- Record confidence
- Confident
Sources
Where this record came from and when it was last checked.
- Reference
- Large-scale learning with svm and convolutional nets for generic object categorization
- Last updated
- 28 November 2025
What the numbers mean
What this model is
Hybrid CNN/SVM Object Categorizer was published by Courant Institute of Mathematical Sciences, in United States of America, in June 2006. The organisation is categorised as academia.
It works in Vision, and is recorded as doing object recognition, Image classification.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
How it was trained
Producing it required around 9.8 × 10¹³ FLOP of arithmetic, which is a statement about the training budget rather than about inference.
It was trained on about 291,600 tokens of text.
Answers
Hybrid CNN/SVM Object Categorizer — common questions
What GPU do I need to run Hybrid CNN/SVM Object Categorizer?
None. Hybrid CNN/SVM Object Categorizer 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 Hybrid CNN/SVM Object Categorizer open source?
No. Hybrid CNN/SVM Object Categorizer has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does Hybrid CNN/SVM Object Categorizer have?
Hybrid CNN/SVM Object Categorizer has 3.6M parameters. For the CNN: "In this case, the whole network has a total of 90,857 trainable parameters." For the SVM: there are 6 binary SVM models trained support vectors = 0.02x291600 dimension = 100 parameters = (0.02x291600)x100x6=3499200 Total = 3590057. 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 Hybrid CNN/SVM Object Categorizer?
Hybrid CNN/SVM Object Categorizer was published by Courant Institute of Mathematical Sciences, based in United States of America, categorised as academia.
When was Hybrid CNN/SVM Object Categorizer released?
Hybrid CNN/SVM Object Categorizer was published in June 2006. 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 Hybrid CNN/SVM Object Categorizer used for?
Hybrid CNN/SVM Object Categorizer works in Vision, and is recorded as handling object recognition, 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 Hybrid CNN/SVM Object Categorizer?
Around 9.8 × 10¹³ 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.
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.