June 2018
Intermediate to advanced
436 pages
10h 33m
English
Since we already know that this is a multi-label multiclass image classification problem, we have to deal with the multiple-instance issue. Since DL4J does not provide an example of how to solve a multi-label multiclass image classification problem, I found Andrew Brooks's blog article (see http://brooksandrew.github.io/simpleblog/articles/convolutional-neural-network-training-with-dl4j/) motivation for this project.
I simply applied the labels of the restaurant to all of the images associated with it and treated each image as a separate record. To be more technical, I handled each class as a separate binary classification problem. Nevertheless, at the beginning of this project, we will see how to read images ...