Skip to content

README.md

Latest commit

 

History

History
26 lines (20 loc) · 1.13 KB

README.md

File metadata and controls

26 lines (20 loc) · 1.13 KB
Raw

Where is the emotion? Dissecting a multi-gap network for image emotion classification

Code written in Tensorflow.keras

Description

Classify emotion into 8 emotion categories.

MG network architecture

Train

  1. Download FI dataset
  2. Store images in data folder groupby emotion classes.
  3. Split data with 'split_data.py'
  4. Run object.py and places.py (Change directory to training_models folder)
  5. Run late_fusion2.py (Change directory to training_models folder)

Use Pretrained Models

  1. Download FI pretrained weights, Store them in pretrained_models folder
  2. Store test images in data/test folder.
  3. Run late_fusion2.py

Demo App with Streamlit

  1. !pip install streamlit
  2. Run demo.py script with command streamlit run demo.py

Acknowledgement

Part of this code is borrowed from GKalliatakis respository.