brand-detector / README.md
rONIVALDO's picture
Update README.md
d47ed9d
---
tags:
- image-classification
- pytorch
- huggingpics
metrics:
- accuracy
model-index:
- name: brand-detector
results:
- task:
name: Image Classification
type: image-classification
metrics:
- name: Accuracy
type: accuracy
value: 0.8428270220756531
---
# brand-detector
Brand detector is a particular case of image classification, since these may contain only text, images, or a combination of both.
In this work, we trained a system for the brand classification of shoes available at https://www.shooos.com/.
The method allows obtaining the most similar brands on the basis of their shape, color, business sector, semantics, general characteristics, or a combination of other features.
The proposed approach is evaluated using 15% of unseen images of the dataset. The experimentation carried out attained reliable performance results, both quantitatively and qualitatively.
How to test:
- find on Google Images any image related to shoe brands below and test it!
This model is not fully trained yet :D
## Example Images
#### adidas
![adidas](images/adidas.jpg)
#### arkk-copenhagen
![arkk-copenhagen](images/arkk-copenhagen.jpg)
#### asics
![asics](images/asics.jpg)
#### birkenstock
![birkenstock](images/birkenstock.jpg)
#### bjorn-borg
![bjorn-borg](images/bjorn-borg.jpg)
#### by-garment-makers
![by-garment-makers](images/by-garment-makers.jpg)
#### camper
![camper](images/camper.jpg)
#### carhartt-wip
![carhartt-wip](images/carhartt-wip.jpg)
#### caterpillar
![caterpillar](images/caterpillar.jpg)
#### champion
![champion](images/champion.jpg)
#### chpo
![chpo](images/chpo.jpg)
#### clae
![clae](images/clae.jpg)
#### colorful-standard
![colorful-standard](images/colorful-standard.jpg)
#### converse
![converse](images/converse.jpg)
#### dc-shoes
![dc-shoes](images/dc-shoes.jpg)
#### dedicated
![dedicated](images/dedicated.jpg)
#### dickies
![dickies](images/dickies.jpg)
#### doughnut
![doughnut](images/doughnut.jpg)
#### dr-martens
![dr-martens](images/dr-martens.jpg)
#### fila
![fila](images/fila.jpg)
#### fjallraven
![fjallraven](images/fjallraven.jpg)
#### hanwag
![hanwag](images/hanwag.jpg)
#### happy-socks
![happy-socks](images/happy-socks.jpg)
#### havaianas
![havaianas](images/havaianas.jpg)
#### herschel-supply
![herschel-supply](images/herschel-supply.jpg)
#### iriedaily
![iriedaily](images/iriedaily.jpg)
#### keepcup
![keepcup](images/keepcup.jpg)
#### lefrik
![lefrik](images/lefrik.jpg)
#### loqi
![loqi](images/loqi.jpg)
#### makia
![makia](images/makia.jpg)
#### maloja
![maloja](images/maloja.jpg)
#### new-balance
![new-balance](images/new-balance.jpg)
#### new-era
![new-era](images/new-era.jpg)
#### nike
![nike](images/nike.jpg)
#### norba-clothing
![norba-clothing](images/norba-clothing.jpg)
#### on-running
![on-running](images/on-running.jpg)
#### onitsuka-tiger
![onitsuka-tiger](images/onitsuka-tiger.jpg)
#### palladium
![palladium](images/palladium.jpg)
#### rains
![rains](images/rains.jpg)
#### reebok
![reebok](images/reebok.jpg)
#### saucony
![saucony](images/saucony.jpg)
#### secrid
![secrid](images/secrid.jpg)
#### sneaky
![sneaky](images/sneaky.jpg)
#### stance
![stance](images/stance.jpg)
#### superfeet
![superfeet](images/superfeet.jpg)
#### the-north-face
![the-north-face](images/the-north-face.jpg)
#### timberland
![timberland](images/timberland.jpg)
#### toms
![toms](images/toms.jpg)
#### triwa
![triwa](images/triwa.jpg)
#### under-armour
![under-armour](images/under-armour.jpg)
#### vans
![vans](images/vans.jpg)
#### veja
![veja](images/veja.jpg)