Dog Food Vit Base Patch16 224 In21k
This is an image classification model based on the Vision Transformer (ViT) architecture, specifically designed to distinguish between images of dogs and food.
Downloads 32
Release Time : 6/20/2022
Model Overview
The model is trained on a dataset of dogs and food, capable of distinguishing between images of dogs and food with high accuracy. Suitable for applications requiring automatic classification of these two types of images.
Model Features
High accuracy
Achieves 99.78% accuracy on the test set, demonstrating excellent performance.
Based on ViT architecture
Utilizes the Vision Transformer architecture with the patch16-224-in21k pre-trained model.
Simple and easy to use
Can be easily trained and used via HuggingPics.
Model Capabilities
Image classification
Distinguishing between dogs and food
Use Cases
Image classification
Pet and food recognition
Automatically identifies whether an image contains a dog or food
Accuracy as high as 99.78%
Content filtering
Used to filter or classify content containing dogs or food
Featured Recommended AI Models