I’ve been playing Fantasy Football for a few years now. You get to pick the players you think will perform best in the coming gameweek with a set of constraints such as limited transfer decisions per week, limited amount of money to spend to buy players, limited game formations etc. There are a lot of uncertain factors in this game, but the human action involved each week is to choose some players to transfer out and be replaced by other players....
If you had an image and you wanted to identify what is shown in the image, or if you had products in an image and you wanted to identify the products, you could tag them with a sticker. What would this sticker look like? And how would you detect the sticker? Your sticker must have a design embedded in it which is detectable and decode-able at any distance from the camera, illumination levels, different angles etc....
What am I doing today? I have installed caffe and the required libraries using this really good guide. The aim of my experiment is to fine-tune tha VGG-16 network for classification. The VGG-16 network I use is pre-trained on ImageNet for classification. I will exploit it’s caffemodel to fine-tune the weights for my own purpose.
Data-Preparation Getting the data prepared correctly finishes most of your work.
Step 1- Go to caffe/data folder and create your own data folder there....
Let’s start with the basics! We know that an integer variable is stored in 4 bytes. An integer array would be a consecutive stream of many such 4 bytes. A string of text would store number of bytes proportional to the characters perhaps with a little padding. Storage of numbers and text is understood, but how on earth, would we store an image? How do we turn an image into something that can be processed and stored in memory?...
Task: Use a pre-trained face descriptor model to output a single continuous variable predicting an outcome using Caffe’s CNN implementation. Picture Reference: https://deeplearning4j.org/linear-regression
So, we’re going to take VGG-Face (a model that is pre-trained on Facial Images) and train this model to predict the salary of the person. This sounds daft! How can anyone predict a person’s salary simply by looking at a person’s face? You and I cannot do this....