Skip to content

Building a model for predicting food images using the famous FOOD-101 dataset.

Notifications You must be signed in to change notification settings

robert-kamunde/Food101Project

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

14 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Food101Project

  • This dataset has 101000 images in total. It's a food dataset with 101 categories(multiclass)
    • Each type of food has 750 training samples and 250 test samples
    • The entire dataset is about 5GB in size
  • Use tensorflow-gpu for faster training time

  • You need to have the food-101 dataset in your working directory (otherwise you should change the paths to the food-101 file)

  • Run food101Work.py to create the train set and test set from the dataset.
  • Run Food101Model.py to tune and train the model ( a MobileNetV2 Pretrained model is used and tuned to the food-101 dataset )
  • Run Prediction_food_images.py to predict new food images. ( the images to be predicted here were in the working directory, if you have them in another location you should change the path)

About

Building a model for predicting food images using the famous FOOD-101 dataset.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages