Skip to content

This is simple image classifier of dogs and cats. This model classifies images based on their particular breeds.

Notifications You must be signed in to change notification settings

dnmanveet/Dog-Cat-Classification

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 

Repository files navigation

Dog-Cat-Classification

This Deep Learning Model is built using the a fast.ai library which, has gather a large amount of hype in current day(2019),for its simplicity in code and length of the code we write to built the model. Screenshot from 2019-05-23 21-06-53

The dataset for training the model is taken from following paper Oxford-IIIT Pet Dataset by O. M. Parkhi et al., 2012 which features 12 cat breeds and 25 dogs breeds. My model now need to learn to differentiate between these 37 distinct categories. According to their paper, the best accuracy they could get in 2012 was 59.21%, using a complex model that was specific to pet detection, with separate "Image", "Head", and "Body" models for the pet photos.

The dataset can downloadd by using untar_data function to which we must pass a URL as an argument and which will download and extract the data.

The Model built using fast.ai library is now it is 96% (2019) accurate whch is very much better than the paper accuracy with is 59.12% in 2012.

Releases

No releases published

Packages

No packages published