AIbase
EN
Home
Beit Base Patch16 224 Pt22k Ft22k Finetuned FER2013 7e 05 Finetuned SFEW 7e 05
B

Beit Base Patch16 224 Pt22k Ft22k Finetuned FER2013 7e 05 Finetuned SFEW 7e 05

Developed by lixiqi
An image classification model based on the BEiT architecture, fine-tuned on the FER2013 dataset for facial expression recognition
Image Classification
Transformers
Open Source License:Apache-2.0#Facial Expression Recognition#Fine-tuning Learning Rate 7e-05#Image Classification
Downloads 18
Release Time : 1/10/2023

Model Overview

This model is a vision Transformer based on the BEiT architecture, specifically fine-tuned for facial expression recognition tasks. It was trained on the FER2013 dataset and can recognize 7 basic facial expressions.

Model Features

Based on BEiT Architecture
Utilizes the BEiT vision Transformer architecture with powerful image feature extraction capabilities
Facial Expression Recognition
Optimized specifically for facial expression recognition tasks, capable of identifying 7 basic expressions
Transfer Learning
Pre-trained on ImageNet-22k and then fine-tuned on the FER2013 dataset

Model Capabilities

Image Classification
Facial Expression Recognition
Sentiment Analysis

Use Cases

Human-Computer Interaction
Emotion Recognition System
Used to identify users' facial expressions to determine emotional states
Achieved 52.6% accuracy on the test set
Psychological Research
Emotional Response Analysis
Used for recording and analyzing subjects' emotional responses in psychological experiments
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
EnglishįŽ€äŊ“中文įšéĢ”中文ãĢãģんご
Š 2025AIbase