What is YOLO? YOLO is a single stage object detector. Types of YOLO YOLOv3 YOLOv4 scaled-YOLOv4 YOLOv5
Deep Face
What is Deep Face? Deep Face is API to do face recognition and facial attribute analysis(age, gender, emotion, race). There are 5 methods in Deep Face. Methods of Deep Face Facial At...
Batch Normalization
What is Batch Normalization? It is a way to perform Regularization. Batch normalization normalizes using the mean and variance of the mini-batch, and scaling and shifting are performed using $\gamm...
Dropout
What is Dropout? It is a way to perform Regularization. Dropout is a method of randomly dropping nodes with a certain probability so that they do not participate in learning. Since nodes are omitte...
Data Augmentation
What is Data Augmentation? It is a way to perform Regularization. Data augmentation is a technique to increase the amount of data by applying various transformations to the original dataset. Data...
L2 Regularization
What is L2 Regularization? It is a way to perform Regularization. L2 Regularization is weight decay technique which decrease more faster if the weight is bigger. Thus, as the overall weights get s...
Regularization
What is Regularization? Regularization penalizes the model to prevent it from overfitting. That is, the model increases its potential to generalize by giving up a perfect fit to the training data. ...
Face-Recognition
What is Face-Recognition? In this post, we are not talking about face recognition theory. Instead, we are going to talk about the module face-recognition. It works as same as face recognition. Let...
Blur Detection
How to do Blur Detection? We can get the value of blur by using cv2.Laplacian(src, ddepth, ksize, scale, delta).var() where: src : Grayscaled image. ddepth : Desired depth of th...
Fix Contrast with Histogram Equalization
What is Histogram Equalization? Histogram Equalization adjusts the dynamic range of an image, making it spread more evenly accross the intensity distribution in order to improve contrast. Cumula...