# WuJie1010/Facial-Expression-Recognition.Pytorch

A CNN based pytorch implementation on facial expression recognition (FER2013 and CK+), achieving 73.112% (state-of-the-art) in FER2013 and 94.64% in CK+ dataset

Repository: https://github.com/WuJie1010/Facial-Expression-Recognition.Pytorch
Canonical: https://ross.abutalabs.com/products/facial-expression-recognitionpytorch
Language: Python
License: MIT
License Family: permissive
Topics: facial-expression-recognition, face-recognition, fer2013, ckan-extension
Last push: 2021-06-14T06:35:39+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2971, "days_push": 1906, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1976, forks 567 (observed 2026-08-28T04:06:01.367464+00:00)

## What it is
A PyTorch implementation of CNN-based facial expression recognition achieving state-of-the-art accuracy on FER2013 (73.112%) and CK+ (94.64%) datasets. It includes preprocessing scripts, training/evaluation code for VGG19 and ResNet18 models, and pre-trained models for visualization.

## Use cases
- recognize facial expressions from images
- train a CNN on the FER2013 dataset
- evaluate emotion recognition models on CK+
- visualize expression predictions with a pre-trained model
- plot confusion matrices for expression classification
- reproduce state-of-the-art FER2013 results

## When to choose
- you need a proven baseline for facial expression recognition in PyTorch
- you want pre-trained models for FER2013 or CK+
- you need reproducible training scripts for emotion recognition benchmarks

## When to avoid
- you need real-time video-based expression recognition out of the box
- you require modern architectures beyond VGG19/ResNet18
- you need actively maintained code with recent dependency support (Python 2.7 era)
- your task is general face recognition or identity verification rather than expression classification

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, computer-vision
- domain: computer-vision, machine-learning, deep-learning, image-processing
- platform: python, cross-platform
- tags: facial-expression-recognition, fer2013, ck-plus, pytorch, cnn, vgg19, resnet18, emotion-recognition, pretrained-models

## Member repositories
- WuJie1010/Facial-Expression-Recognition.Pytorch (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:01.367464+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:04:49.115636+00:00, confidence not recorded.
  - readme: https://github.com/WuJie1010/Facial-Expression-Recognition.Pytorch (fetched 2026-08-28T04:06:01.367464+00:00, sha 71dc7cd0b71d)
- Data as of 2026-08-30T08:39:29.467469+00:00.