Mini-Project 3

Select model type and upload image below

Please note that these models are only trained on specific items and are subject to error

Yolo Model

The YOLO (You Only Look Once) model is renowned for predicting bounding boxes and class probabilities in a single pass through the neural network. This model will generate a new image with classifying boxes around different objects that are detected in the image

ViT Transformer Model

The Vision Transformer (ViT) model excels in capturing global contextual information. Choosing this model will give you the object or objects with the highest probablity found in the image.