Real Time Ai -Self Learning Model ,where user will give an input of an object,and Ai will follow this complete automated process of self Learning-
1 Google Search the images of the object
2 Learn the shape and size of the object and tag objects in the image
3 Make train data from those images
4 Tag/Label the object inside the image
5 Write down all the appropriate annotations and text files required for YOLO Model
6 Edit YOLO YAML file with appropriate configurations
7 Train the images, make inference graph, and then Robot will finally know what “keys” are, so it can open up the Camera and start looking for it
https://towardsdatascience.com/computer-vision-object-location-through-ai-self-learning-52467ef3fb99