A lot of times, we come across new dishes and wonder what kind of food that is. Well, this app will be there to help you up in real time. Just point your camera towards the food and it will tell what kind of food it is instantly. And yeah, this app works offline.

A lot of times, we come across new dishes and wonder what kind of food that is. Well, this app will be there to help you up. Just point your camera towards the food and it will tell what kind of food it is instantly. And yeah, this app works offline.

It has a model trained to recognize food categories and uses your phone"s camera to recognize the food that your camera is seeing by passing the frames through the model.

• Dart
• Flutter
• Keras
• Python
• Tensorflow Lite

This Food Classification model with 11-classes uses Python with Tensorflow framework. I trained my own Convolutional Neural Network using Transfer Learning from the very famous InceptionResnetV2 using the "Food-11" dataset from Kaggle.

After training the model I converted it to Tensorflow Lite which made it easier for deploying on a mobile device.

1. Download the mentioned dataset
2. Uncomment everything
3. Go to this repository and train the model by using

python claasifier.py

4. Now go to the same repository and test the model using

python assess.py

The conversion to TFLite takes place within the claasifier.py file mentioned above.

To build, just use

flutter pub get
flutter run

in the root directory of this project.

• Adding support for more categories, like even identifying what food it is
• Making a better UI (this current one is just a barebone)
• Optimizing performance
• Probably even add an option to get a recipe to make that food.

Check it out!!