Home

Awesome

Sentiment Vision Demo

A Demo application using Vision and CoreML frameworks to detect the most likely sentiment of the given image.

<div align="center"> <img src="https://github.com/cocoa-ai/SentimentVisionDemo/blob/master/Screenshot.png" alt="SentimentVisionDemo" width="300" height="416" /> </div>

Model

This demo is based on the "Fine-tuning CNNs for Visual Sentiment Prediction" neural network classifier, which was converted from original Caffe model to CoreML model using coremltools python package.

Requirements

Installation

git clone https://github.com/cocoa-ml/SentimentVisionDemo.git
cd SentimentVisionDemo
pod install
open SentimentVision.xcworkspace/

Download the CoreMl model and drag the file into your project.

Build the project and run it on a simulator or a device with iOS 11.

Conversion

cd Convert
./download.sh
python convert.py

Author

Vadym Markov, markov.vadym@gmail.com

Credits

From Pixels to Sentiment: Fine-tuning CNNs for Visual Sentiment Prediction

References