The Classifier model type can help you efficiently classify entire images or specific regions into predefined classes.
It outputs labels ranked by confidence (for example, "apple: 80%", "peach 40%") ensuring clear and actionable insights.
Ideal for various use cases, including sorting product images into categories, like fruits (apple, orange, banana) or classifying X-rays as "healthy" or "abnormal", the model operates on the image without pinpointing specific objects, resulting in faster and more accurate results when categorizing precise tasks.
The Detector model type can identify and locate multiple objects within an image.
It outputs bounding boxes around the detected items and labels them with a confidence score (for example, "car: 90%" at (x,y)).
This is great for detecting vehicles and pedestrians in street scenes or counting items on a conveyor belt ("3 apples, 2 oranges") as it effectively identifies what objects are and where they are.
Stay connected – follow us!
X
Body text goes here. Body text goes here. Body text goes here.
Body text goes here. Body text goes here. Body text goes here.
Qiita
Body text goes here. Body text goes here. Body text goes here.
GitHub
Body text goes here. Body text goes here. Body text goes here.
Body text goes here. Body text goes here. Body text goes here.
X
Body text goes here. Body text goes here. Body text goes here.