Keras data augmentation6/3/2023 ![]() Let’s say it doesn’t contain more than a couple thousand images. The data set you were given is to small to develop an efficient solution.See, there are two intimidating problems (OK maybe there is none of them but I will hypothesise it to make my case here). Right, you set up a Convolutional Neural Network, set up your hyper-parameters in the usual (?) way and you are good to go! Or…not. So, you are participating in an Image classification Data Science competition or your boss has assigned you to automatically categorise a gazillion images or you just have so much free time that you decided to learn how to build a Neural Network that can discern between image classes in a given dataset.
0 Comments
Leave a Reply. |