Empty detection results with Faster R-CNN - help!!
4 次查看(过去 30 天)
显示 更早的评论
I am trying to train a Faster R-CNN 2D but I always get empty detection results...
- I use a pre-trained backbone network on my data (which has an accuracy of around 70%);
- The images have size [512 512 1] and are uint8 (as well as the input size of the network);
- The bounding boxes are approximately between 30x30 to 60x60;
- I have 2 classes of objects;
- 250 epochs (already varied it but the result is the same) with MB size 64;
- I've tried it with a very low positive overlap range ([0.1 1]);
- ROI Mas pooling 7x7
- I used fasterRCNNLayers to create a faster R-CNN object.
(500 images+bounding boxes around objects of two classes to train)
Example of training data table:
imageFilename class1 class2
'image1.tiff' [100, 110, 35, 50] []
'image2.tiff' [] [50,20, 40,30]
1) Is there a problem with the images being grayscale and not in color?
2) Do I have to have bounding boxes from a region other than the object? (as described here: https://www.mathworks.com/matlabcentral/answers/500950-bounding-box-not-drawn-some-variables-are-empty).
I really need some help... I don't understand how it runs without errors and then it can't find any object.
Thank you so so much in advance!!!
回答(0 个)
另请参阅
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!