https://github.com/qwinpin/emotion_bot

https://github.com/qwinpin/emotion_bot

bot emotion-recognition keras machine-learning telegram

Last synced: about 12 hours ago
JSON representation

• Host: GitHub
• URL: https://github.com/qwinpin/emotion_bot
• Owner: Qwinpin
• Created: 2018-02-16T11:18:32.000Z (almost 7 years ago)
• Default Branch: master
• Last Pushed: 2018-03-02T13:59:45.000Z (almost 7 years ago)
• Last Synced: 2024-11-15T01:28:46.741Z (2 months ago)
• Topics: bot, emotion-recognition, keras, machine-learning, telegram
• Language: Python
• Size: 55.1 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Emotion recognition bot

Telegram bot and torch model for emotion recognition from face photo.

## Features

1. Detect several faces at once

2. 6 possible emotions: 

   1. Angry

   2. Sad

   3. Surprise

   4. Happy

   5. Fear

   6. Neutral

3. Pretrained model included

4. Easy to deploy

## Installation

1. Install [pytorch](http://pytorch.org/)

2. Install [opencv-python](https://pypi.python.org/pypi/opencv-python)

3. Install pygal

4. Install [Pillow](https://github.com/python-pillow/Pillow) (Fork from PIL)

5. Edit config.py with your telegram token

6. Run listener.py

"Challenges in Representation Learning: A report on three machine learning

contests." I Goodfellow, D Erhan, PL Carrier, A Courville, M Mirza, B

Hamner, W Cukierski, Y Tang, DH Lee, Y Zhou, C Ramaiah, F Feng, R Li,

X Wang, D Athanasakis, J Shawe-Taylor, M Milakov, J Park, R Ionescu,

M Popescu, C Grozea, J Bergstra, J Xie, L Romaszko, B Xu, Z Chuang, and

Y. Bengio. arXiv 2013.