Posted on

Machine Learning Algorithms and GAN

Today’s world is running behind the concept of machines performing activities similar to that of humans in a much more efficient way. But, have you ever wondered, from where these machines gained so much intelligence?? Is it in-build to have a brain as humans or were they trained to perform these activities?

To implement these basic activities, there is a certain amount of experience is required by the computer. This intelligence to perform tasks is gifted to the machines by ML algorithms which help us for the automated tasks. Now, Let us dive deep into the ML algorithms and understand their importance. 

Posted on

How We Trained a Neural Network to Generate Shadows in a Photo: Part 2

In this series, Artem Nazarenko, Computer Vision Engineer at Everypixel shows you how you can implement the architecture of a neural network. In the first part, we were talking about the working principles of GAN and methods of collecting datasets for training. This part is about preparing for GAN training.

Loss Functions and Metrics

Attention. At this point, we deviate from the reference article. We take the loss function to solve the segmentation problem. Generation of attention maps (masks) can be considered as a classic image segmentation problem. We take Dice Loss as the loss function. It is well resilient to unbalanced data.