AffectNet is a large facial expression dataset with around 0.4 million images manually labeled for the presence of eight (neutral, happy, angry, sad, fear, surprise, disgust, contempt) facial expressions along with the intensity of valence and arousal.

chitradrishti/AffectNet dataset hosted on Hugging Face and contributed by the HF Datasets community

This dataset AFFECTNET YOLO Format is aimed to be used in facial expression detection for a YOLO project...

Affectnet P2

## Overview

Affectnet P2 is a dataset for object detection tasks - it contains Emotions annotations for 7,158 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [BY-NC-SA 4.0 license](https://creativecommons.org/licenses/BY-NC-SA 4.0).

The Balanced Affectnet Dataset is a uniformly processed, class-balanced, and augmented version of the affect-fer composite dataset. This curated version is tailored for deep learning and machine learning applications in Facial Emotion Recognition (FER). It addresses class imbalance and standardizes input dimensions to enhance model performance and comparability.

🎯 Purpose The goal of this dataset is to balance the representation of seven basic emotions, enabling the training of fairer and more robust FER models. Each emotion class contains an equal number of images, facilitating consistent model learning and evaluation across all classes.

🧾 Dataset Characteristics Source: Based on the Affectnet dataset

Image Format: RGB .png

Image Size: 75 × 75 pixels

Emotion 8-Classes: Anger Contempt disgust fear happy neutral sad surprise

Total Images: 41,008

Images per Class: 5,126

⚙️ Preprocessing Pipeline Each image in the dataset has been preprocessed using the following steps:

✅ Converted to grayscale

✅ Resized to 75×75 pixels

✅ Augmented using:

Random rotation

Horizontal flip

Brightness adjustment

Contrast enhancement

Sharpness modification

This results in a clean, uniform, and diverse dataset ideal for FER tasks.

Testing (10%): 4100 images

Training (80% of remainder): 29526 images

Validation (20% of remainder): 7,382 images

✅ Advantages ⚖️ Balanced Classes: Equal images across all seven emotions

🧠 Model-Friendly: Grayscale, resized format reduces preprocessing overhead

🚀 Augmented: Improves model generalization and robustness

📦 Split Ready: Train/Val/Test folders structured per class

📊 Great for Benchmarking: Ideal for training CNNs, Transformers, and ensemble models for FER

oscarparro/emotion-images-affectnet dataset hosted on Hugging Face and contributed by the HF Datasets community

The dataset is made from careful collection of images from a largely used dataset called AffectNet. This dataset contains only 3 emotions: 1. Confidence 2. Confusion 3. Nervousness

I have created a project using this dataset, which can be found in the github.

harveymannering/affectnet-512 dataset hosted on Hugging Face and contributed by the HF Datasets community

Dataset

This dataset was created by Aldhaneka

Contents

Comparison of experimental results on the Affectnet dataset.

Dataset

This dataset was created by SHANTANU PANDEY

Released under MIT

Contents

This model is trained on the AffectNet dataset to classify emotions into two categories: neutral and stress. For the neutral class, the dataset includes emotions labeled as happy, surprise, and neutral, while the stress class combines emotions labeled as contempt, angry, fear, and sad. Designed for the CalmScope application, the model detects signs of stress through facial expressions. It has been trained and optimized using Roboflow to ensure accurate and reliable performance in real-world scenarios.

The FER+ dataset is an extension of the original FER dataset, where the images have been re-labelled into one of 8 emotion types: neutral, happiness, surprise, sadness, anger, disgust, fear, and contempt.

Explore our diverse Image Inpainting, curated by AI students in 2022. Perfect for training image reconstruction models, this dataset features random objects and scenic views.

Dataset

This dataset was created by muhsmmsd

Released under Apache 2.0

Contents

Dataset

This dataset was created by Jishnusaravanan

Contents