Info
This question is closed. Reopen it to edit or answer.
How can I train CNN model with a dataset, whos image have mulitiple features
1 view (last 30 days)
Show older comments
![1.png](https://www.mathworks.com/matlabcentral/answers/uploaded_files/210586/1.png)
1 My data set is like the above image, each image has multi -features, All the image has the same size in height and width 1300x290
2I use image labeler to label the feature ,and got the dataset, as following.
![2.png](https://www.mathworks.com/matlabcentral/answers/uploaded_files/210587/2.png)
3 I use a typical layer to train the CNN, as following.
![3.png](https://www.mathworks.com/matlabcentral/answers/uploaded_files/210588/3.png)
4
Then I try the model
detector = trainFasterRCNNObjectDetector(trainingData, layers, options, ...
'NegativeOverlapRange', [0 0.3], ...
'PositiveOverlapRange', [0.6 1], ...
'NumRegionsToSample', [256 128 256 128], ...
'BoxPyramidScale', 1.2);
5 but failed, many erros happens.
![4.png](https://www.mathworks.com/matlabcentral/answers/uploaded_files/210589/4.png)
6My quesiton is how to train a CNN model with the dataset ,where one image has several features?
0 Comments
Answers (0)
This question is closed.
See Also
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!