Open-source finetuned-affecthq Image Classification Model - Accurately identify images and is incredibly practical for free deployment!

Finetuned Affecthq

Developed by Piro17

An image classification model fine-tuned based on google/vit-base-patch16-224-in21k, trained on an image folder dataset with an evaluation accuracy of 71.79%.

Image Classification

Transformers

Open Source License:Apache-2.0 #ViT fine-tuned model #Image emotion classification #High accuracy

Downloads 18

Release Time : 2/16/2023

Model Overview

This model is an image classification model based on the Vision Transformer (ViT) architecture, fine-tuned for specific image classification tasks.

Model Features

High-precision classification

Achieves 71.79% accuracy and 71.67% F1 score on the evaluation set.

ViT-based architecture

Utilizes the Vision Transformer architecture with powerful image feature extraction capabilities.

Fine-tuning

Fine-tuned on google/vit-base-patch16-224-in21k to adapt to specific classification tasks.

Model Capabilities

Image classification

Visual feature extraction

Multi-class recognition

Use Cases

Image analysis

General image classification

Classifies and identifies input images.

71.79% accuracy

🚀 finetuned-affecthq

This model is a fine - tuned version of [google/vit - base - patch16 - 224 - in21k](https://huggingface.co/google/vit - base - patch16 - 224 - in21k) on the imagefolder dataset, achieving good performance in image classification tasks.

🚀 Quick Start

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

Loss: 0.8116
Accuracy: 0.7179
Precision: 0.7174
Recall: 0.7179
F1: 0.7167

📚 Documentation

Model Details

Property	Details
Model Type	Fine - tuned version of [google/vit - base - patch16 - 224 - in21k](https://huggingface.co/google/vit - base - patch16 - 224 - in21k)
Training Data	imagefolder
Metrics	Accuracy, Precision, Recall, F1

Training Procedure

Training Hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e - 05
train_batch_size: 32
eval_batch_size: 32
seed: 17
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 10

Training Results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
1.5413	1.0	174	1.4810	0.4898	0.4867	0.4898	0.4409
1.0367	2.0	348	1.0571	0.6155	0.6172	0.6155	0.6041
0.9534	3.0	522	0.9673	0.6475	0.6476	0.6475	0.6375
0.8532	4.0	696	0.9056	0.6748	0.6710	0.6748	0.6704
0.8211	5.0	870	0.8707	0.6903	0.6912	0.6903	0.6836
0.7797	6.0	1044	0.8472	0.7050	0.7050	0.7050	0.7019
0.7816	7.0	1218	0.8298	0.7111	0.7099	0.7111	0.7096
0.7135	8.0	1392	0.8186	0.7111	0.7116	0.7111	0.7105
0.6697	9.0	1566	0.8143	0.7140	0.7124	0.7140	0.7126
0.6765	10.0	1740	0.8116	0.7179	0.7174	0.7179	0.7167

Framework Versions

Transformers 4.27.0.dev0
Pytorch 1.13.1+cu116
Datasets 2.9.0
Tokenizers 0.13.2

📄 License

This model is licensed under the Apache 2.0 license.

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