Pular para o conteúdo principal

Postagens

Mostrando postagens com o rótulo yolo

Detecting objects in a JavaFX application using YOLOv2 and DeepLearning4J

A few months ago we published  here the post Detecting Objects using JavaFX and Deep Learning . Recently it was added to Eclipse DeepLearning4J a new model: Yolo2, which is based on YoloV2. It is already available in maven central on DL4J 1.0.0-beta version. Using the application from our older post we just modified two lines of Java code (see the commit )   to use YOLOv2 from the JavaFX application we built earlier. The result is a more precise detector with more classes! If you want to try it just follow the instruction from my previous post . I hope next time I can test YOLOv3, which is the state-of-the-art deep learning model for object detection!  Deep Learning in Java is possible and easy to use due DL4J developers hard work, so thank you guys, you are amazing.

Detecting objects using JavaFX and Deep Learning

Computer vision meets Deep Learning mainly due the use of Convolutional Neural Networks . We have used it in our blog already for labeling images. Another challenging area of Deep Learning and computer vision is to identify the position of objects and for this we have a great neural network technique (or architecture - you choose the best) called YOLO . The following video will show you the power of YOLO neural networks: The output of a neural network such as Resnet50 is a vector with probabilities of labels. So you feed it with an image that contains a cat, it will output various float numbers in an array, each position of that array is a label and the value on that position is the possibility of that label. As an example let's think about a neural network that should recognize dogs (0) and cats (1), and you feed it with an image of a cat, it should output an array of two positions and 0% in position 0 (which represents dog) and 100% in position 1 (which represents cat). Th...