Skip to content

A CNN model to classify given image input into a whooping 131 different classes of fruits and veggies

Notifications You must be signed in to change notification settings

Dominastorm/Fruits-n-Veggies-Classifier

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 

Repository files navigation

Fruits-n-Veggies-Classifier

Contributors:

Dhruv Chawla 

Aaryansh Bhargavan

Phaneesh R Katti

A CNN model to classify given image input into a whooping 131 different classes of fruits and veggies

Here we use the fruits-360 kaggle dataset(https://www.kaggle.com/moltean/fruits) to train a CNN model to learn to classify objects into 131 varities of fruits and vegetables

The dataset by default has about 90,000 images of which 75% are training images images are of resolution 100x100 pixels We have used InceptionV3 Architecture for Transfer Learning, as well as Data Augmentation

The 131 classes have been named in the pre-defined order and must not be changed Model is trained for 30 epochs and gives reasonably good accuracy

Video presentation: https://drive.google.com/drive/u/0/folders/1pvuebms0wIzaXzCSbQfcJH11q9O9CwJT (Be sure to follow certain in script instructions to get the o/p)

About

A CNN model to classify given image input into a whooping 131 different classes of fruits and veggies

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 100.0%