MATLAB Answers

How to perform Faster RCNN on my own dataset in Matlab?

15 views (last 30 days)
Ibrahim Hassan Syed
Ibrahim Hassan Syed on 11 Feb 2020
Commented: Hayat Bouchkouk on 22 Mar 2020
I am using Matlab Faster RCNN example which use its own dataset (Vehicle dataset). I want to use my own dataset to train Faster RCNN. Can anyone please let me know how can I load my own dataset? I have also created ground truth.
I have confusion here. How can I add my own data here?
data = load('fasterRCNNVehicleTrainingData.mat');
trainingData = data.vehicleTrainingData; trainingData.imageFilename = fullfile(toolboxdir('vision'),'visiondata', ... t
rainingData.imageFilename);

  1 Comment

Hayat  Bouchkouk
Hayat Bouchkouk on 22 Mar 2020
hi Ibrahim Hassan Syed
i have a same problem with dataset can i help me how can i load coco dataset in matlab?plizz

Sign in to comment.

Answers (1)

Sourav Bairagya
Sourav Bairagya on 14 Feb 2020
After you prepared ground truth from your dataset, load that ground truth data. Now, extract the training data from that ground truth object. This training data is stored in a two-column table format, where the first column contains the image file paths and the second column contains the vehicle bounding boxes.
data = load('fasterRCNNVehicleTrainingDataGroundTruth.mat');
vehicleDataset = data.vehicleTrainingData;
Now, you can follow the steps as mentioned in this following example for arranging your dataset for training.

  0 Comments

Sign in to comment.

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!