I want to create my own training data using the following link: https://in.mathworks.com/help/vision/ref/trainrcnnobjectdetector.html I am facing problem in crating the load arguments. load('rcnnStopSigns.mat', 'stopSigns', 'layers')
I just want to know what rcnnStopSings.mat consists of and stopSign table consist of and how I should create these two
Here 'rcnnStopSigns.mat' is a mat file which contains the two tables namely 'stopSigns' and 'layers' . I am attaching both the tables here for your reference. The stopSigns table contains two columns with one the image location and the other column mentioning its coordinate of the region of interest. The layers table consist of the deep learning layers available for the rcnn network that you are going to train.
You can create both these tables on your own and can save it in a new 'xyz.mat' file using save command and use it for rcnn training .
You need ground truth data for training. So, you need a set of images with bottles in them and bounding boxes for the bottles in the images.
The mat file just contains an array of structs specifying the name of the image file and the bounding box of the bottle in that image.
Read this: http://www.mathworks.com/help/vision/ref/traincascadeobjectdetector.html#inputarg_positiveinstances
The mat file is just used to pass the positive instances input argument to the trainCascadeObjectDetector function.
- Badges
- Science topic
- Similar topics
- Organizational Psychology
- Training