https://github.com/ph1ps/Food101-CoreML

A CoreML model which classifies images of food
https://github.com/ph1ps/Food101-CoreML

convolutional-neural-networks coreml coreml-framework coreml-models food-classification machine-learning machine-learning-models

Last synced: 3 months ago
JSON representation

A CoreML model which classifies images of food

• Host: GitHub
• URL: https://github.com/ph1ps/Food101-CoreML
• Owner: ph1ps
• License: mit
• Archived: true
• Created: 2017-07-09T20:11:00.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2018-02-15T17:12:28.000Z (almost 7 years ago)
• Last Synced: 2024-08-03T17:10:02.727Z (7 months ago)
• Topics: convolutional-neural-networks, coreml, coreml-framework, coreml-models, food-classification, machine-learning, machine-learning-models
• Language: Swift
• Size: 3.73 MB
• Stars: 144
• Watchers: 8
• Forks: 32
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-CoreML-models - Food101-CoreML

README

        
# Food101 for CoreML

### Description

This is the Food101 dataset implemented in Apple's new framework called CoreML. The Food101 dataset can predict foods from images. The model was built with Keras 1.2.2 and is a **fine-tuned InceptionV3 model**.

To test this model you can open the `Food101Prediction.xcodeproj` and run it on your device (iOS 11 and Xcode 9 is required). To test further images just add them to the project and replace my testing with yours.

### Obtaining the model

*  [Download](https://drive.google.com/open?id=0B5TjkH3njRqnVjBPZGRZbkNITjA) the model from Google Drive and drag it right into your project folder

* Convert the model on your own:

  1. Change directory:  `cd ./Convert`

  2. Change directory:  `sh convert.sh`

  

### More information

  If you want to find out more how this model works and on which data it was trained on, feel free to visit the original Food101 Keras page on [Github](https://github.com/stratospark/food-101-keras)

  

### Examples