YOLO stands for “You Look Only Once” and is an extremely fast object detection framework that uses a single convolutional neural network. YOLO is generally faster than other object detection systems because it looks at the entire image at once, rather than scanning the image pixel-by-pixel. YOLO does this by dividing an image into a grid, and then each part of the grid is classified and localized (i.e. objects and structures are created). Then it predicts where to place the bounding boxes. The estimation of these bounding boxes is done with regression based algorithms as opposed to classification based algorithms.
Generally, classification-based algorithms are completed in two steps:
- Selecting the region of interest (ROI — Region of Interest)
- Application of convolutional neural network (CNN) to selected regions to detect the object(s).
YOLO’s regression algorithm estimates the bounding boxes for the entire image at once, making it significantly faster and a great option to boot.
The definition of topics such as computer vision, artificial neural networks, machine learning is not the subject of this article. In short, YOLO is an open source computer vision framework or library written in Python.
What are the must-haves on your computer?
First of all, I should point this out. Python coders know that Anaconda software is extremely slow and confusing at downloading and installing libraries. Of course, you can go and write your Python codes with the software (Spyder, PyCharm, etc.) there, but do not confuse the Python path you downloaded locally with Anaconda’s!
So that all this does not happen, we will make it possible for you to install and work with YOLO in the cleanest way, without messing with Anaconda, in the way I will explain now. Here are the things you need to install:
....
Read the full article and give it a clap on Medium: Article here
Top comments (6)
nice article tho
yea
thx broooooo
claaaaaaaap
xd
thank uuuuuuuu