MATLAB: Dot indexing is not supported for variables of this type

Deep Learning Toolboxr-cnn

Hi,

I get the error message in the following images, how can i fix it?

Thank you.

Best Answer

The downloaded .mat is not compatible with R2019a; it works with R2019b though.

Related Solutions

MATLAB: Train a trained object detector with more epochs

First of all, the title is not clear.

I found the answer which is called resume training. (https://www.mathworks.com/help/deeplearning/ug/resume-training-from-a-checkpoint-network.html)

But my condition is different from the offcical website example. I used function trainFasterRCNNObjectDetector and the type of my network is DAGNetwork. As a result, the solution for my situation is shown below

load('rcnn.mat');                 % Load previously trained network.
net = layerGraph(rcnn.Network);   % Transform DAGNetwork to make it excutable for trainFasterRCNNObjectDetector.
rcnn = trainFasterRCNNObjectDetector(trainingImages, layerGraph(net), options);
save('rcnn.mat', 'rcnn');         % Save trained network.

MATLAB: What is the difference between rcnnStopSigns.mat and stopSigns in the function load(‘rcnnStopSigns.mat’, ‘stopSigns’, ‘layers’) of trainRCNNObjectDetector. https://in.mathworks.com/help/vision/ref/trainrcnnobjectdetector.html.

That line of code loads a variable named stopSigns (and a variable named layers) from a MAT-file named rcnnStopSigns.mat. The variable is stored inside the MAT-file.

Best Answer

Related Solutions

MATLAB: Train a trained object detector with more epochs

MATLAB: What is the difference between rcnnStopSigns.mat and stopSigns in the function load(‘rcnn​StopSigns.​mat’, ‘stopSigns’, ‘layers’) of trainRCNNObjectDetector. https://in​.mathworks​.com/help/​vision/ref​/trainrcnn​objectdete​ctor.html.

Related Question

MATLAB: What is the difference between rcnnStopSigns.mat and stopSigns in the function load(‘rcnnStopSigns.mat’, ‘stopSigns’, ‘layers’) of trainRCNNObjectDetector. https://in.mathworks.com/help/vision/ref/trainrcnnobjectdetector.html.