vit-base-avengers-v1 Open-Source Image Classification Model - Accurately Identify Avengers Characters with Nearly 87% Accuracy

Vit Base Avengers V1

Developed by dingusagar

A Vision Transformer-based Avengers character classification model achieving 86.83% accuracy on image classification tasks

Image Classification

Transformers

Open Source License:Apache-2.0 #Avengers Character Recognition #High Accuracy Image Classification #Vision Transformer Fine-tuning

Downloads 30

Release Time : 7/9/2022

Model Overview

This model is fine-tuned from Google's ViT model, specifically designed to recognize superhero characters from the Avengers.

Model Features

High Accuracy

Achieves 86.83% accuracy on Avengers character classification tasks

ViT-based Architecture

Utilizes Vision Transformer architecture for effective image classification

Domain-Specific Optimization

Specially optimized for Avengers characters, outperforming general-purpose models

Model Capabilities

Image Classification

Superhero Recognition

Visual Feature Extraction

Use Cases

Entertainment Applications

Character Recognition App

Develop mobile apps to identify Avengers characters in movies or comics

Accurately recognizes 16 major Avengers characters

Content Categorization

Automatically categorize images containing Avengers characters in media libraries

🚀 vit-base-avengers-v1

This model is a fine - tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset, achieving high accuracy in image classification tasks.

🚀 Quick Start

This model is a fine - tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.5324
Accuracy: 0.8683

Refer to this medium article for more info on how it was trained.

✨ Features

High Accuracy: Achieves an accuracy of 0.8683 on the evaluation set.
Fine - Tuned: Based on the pre - trained google/vit-base-patch16-224-in21k model.

📚 Documentation

Limitations

Training was done on google images for these search terms each representing a class. Iron Man,Captain America,Thor,Spider Man,Docter Strage,Black Panther,Ant Man,Captain Marvel,Hulk,Black Widow,Hawkeye Avengers,Scarlet Witch,Vision Avengers,Bucky Barnes,Falcon Avengers,Loki

Therefore it has seen more of images where these super heros are in their suit or superhero outfit. For example an image of hulk is detected correctly, but an image of Bruce Banner is not simply because the model has't seen those images. A little bit of data augmentation will help.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 16
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e - 08
lr_scheduler_type: linear
num_epochs: 4
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.8183	1.27	100	1.0134	0.8464
0.2234	2.53	200	0.6146	0.8495
0.1206	3.8	300	0.5324	0.8683

Framework versions

Transformers 4.20.1
Pytorch 1.11.0+cu113
Datasets 2.3.2
Tokenizers 0.12.1

📄 License

This model is licensed under the Apache - 2.0 license.

Property	Details
Model Type	vit-base-avengers-v1
Training Data	imagefolder dataset (avengers - dataset)
Metrics	accuracy
License	apache - 2.0

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご