Swin-Tiny-Finetuned Dog Food Open-Source Model - Accurately Classify Dog Food Images with Nearly 99% Accuracy

Swin Tiny Finetuned Dogfood

Developed by sasha

A dog food image classification model fine-tuned based on Swin Transformer Tiny architecture, achieving 98.8% accuracy on the test set

Image Classification

Transformers

Open Source License:Apache-2.0 #High-precision Image Classification #Pet Food Recognition #Swin Transformer Fine-tuning

Downloads 15

Release Time : 6/26/2022

Model Overview

This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on a dog food image dataset, specifically designed for image classification tasks of dog food products.

Model Features

High Accuracy

Achieves 98.8% classification accuracy on the test set

Fine-tuned Model

Fine-tuned based on the pre-trained Swin Transformer Tiny architecture

Comprehensive Evaluation Metrics

Provides multi-dimensional evaluation metrics including accuracy, precision, recall, and F1 score

Model Capabilities

Image Classification

Dog Food Product Recognition

Use Cases

Pet Food Industry

Dog Food Product Classification

Automatically identifies and classifies different brands or types of dog food products

Accuracy reaches 98.8%

Retail Inventory Management

Used for automated inventory management systems in supermarkets or pet stores

🚀 swin-tiny-finetuned-dogfood

This model is a fine - tuned version of [microsoft/swin - tiny - patch4 - window7 - 224](https://huggingface.co/microsoft/swin - tiny - patch4 - window7 - 224) on the lewtun/dog_food dataset. It can achieve high - accuracy image classification on the dog food dataset, providing reliable results for related tasks.

🚀 Quick Start

This model is a fine - tuned version of [microsoft/swin - tiny - patch4 - window7 - 224](https://huggingface.co/microsoft/swin - tiny - patch4 - window7 - 224) on the lewtun/dog_food dataset. It achieves the following results on the evaluation set:

Loss: 0.1959
Accuracy: 0.988

📄 License

The model is licensed under the Apache - 2.0 license.

📚 Documentation

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: 5e - 05
train_batch_size: 32
eval_batch_size: 32
seed: 42
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: 1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.8198	1.0	16	0.1901	0.9822

Framework versions

Transformers 4.20.1
Pytorch 1.11.0+cu113
Datasets 2.3.2
Tokenizers 0.12.1

📦 Model Information

Property	Details
Model Type	Generated from trainer
Training Datasets	imagefolder, lewtun/dog_food
Metrics	accuracy
Model Name	swin - tiny - finetuned - dogfood
Results	Task 1: Image Classification on lewtun/dog_food dataset, Accuracy = 0.988 Task 2: Image Classification on test split of lewtun/dog_food dataset, Accuracy = 0.9826666666666667, Precision Macro = 0.9820904286553143, Precision Micro = 0.9826666666666667, Precision Weighted = 0.9828416519866903, Recall Macro = 0.9828453314981092, Recall Micro = 0.9826666666666667, Recall Weighted = 0.9826666666666667, F1 Macro = 0.9824101123169301, F1 Micro = 0.9826666666666667, F1 Weighted = 0.9826983433609648, Loss = 0.2326570302248001, Matthews Correlation = 0.974016655798285

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