datahacker.rs@gmail.com

# Category: Machine Learning

### #027 CNN Non-Max Suppression algorithm

Non-Max Suppression In this post, we will learn how the non-max suppression algorithm allows us to overcome multiple detections of the same object in an image. Let’s go through an example! Let’s say we want to detect pedestrians, cars, and motorcycles in this image. If we look at the picture above we can see that there are two cars. Each of these two cars has one midpoint so it should be assigned to just one…

### #026 CNN Intersection over Union

Intersection over Union In this post, we will learn about a function called Intersection over union. We will use this to make our object detection algorithm to work even better. How do we tell if our object detection algorithm is working well? When doing the object detection our task is to localize the object in the best possible way. Take a look at the picture above we can see that there are two bounding boxes…

### #025 CNN Bounding Box Predictions

Bounding box predictions In the last post, we learned how to use a convolutional implementation of sliding windows. That’s more computationally efficient, but it still has a problem of not outputting the most accurate bounding boxes.  In this post, we will see how we can obtain more accurate predictions of bounding boxes.  Output accurate bounding boxes With sliding windows, we take the sets of windows that we move throughout the image and we obtain a set of sliding…
$$Inception\enspace network$$  Motivation for the $$Inception\enspace network$$: In the last post we talked about why $$1\times 1$$ convolutional layer can be useful and now we will use it for building the $$Inception\enspace network$$. When designing a layer for a $$convnet$$ we might have to choose between a $$1 \times 3$$ filter, a $$3 \times 3$$ or $$5\times 5$$ or maybe a pooling layer. An $$Inception\enspace network$$ solves this…
Convolutional Neural Network – An Example In previous posts (CNN 004, CNN 005 and CNN 009) we have defined all building blocks for building a full convolutional neural network. Let’s now look at an example of a convolutional neural network (CNN). Let’s say that we have a $$32 \times 32 \times 3$$ dimensional image as an input to the CNN. So it’s an RGB image and supoose we want to try to do a handwritten… 