Clear Filters
Clear Filters

Training FasterRCNNObjectDetector with LayerGraph error with MinBoxSizes

2 views (last 30 days)
When running the training instruction for a Faster RCNN with a LayerGraph the 'MinBoxSizes' parameter won't let it start:
Error using vision.internal.cnn.parseInputsFasterRCNN (line 67)
'MinBoxSizes' is not supported when the input network is a LayerGraph.
Error in trainFasterRCNNObjectDetector (line 333)
vision.internal.cnn.parseInputsFasterRCNN(...
Error in FRCNN (line 86)
detector = trainFasterRCNNObjectDetector(images, lgraph, options, ...
The documentation states that:
"You cannot use this property if you set the network to a LayerGraph object or if you resume training from a detector checkpoint."
And my options don't have the 'MinBoxSizes' parameter set, so it goes automatically on 'auto', not allowing the training.
detector = trainFasterRCNNObjectDetector(images, lgraph, options, ...
'NegativeOverlapRange', [0 0.3], ...
'PositiveOverlapRange', [0.6 1], ...
'BoxPyramidScale', 1.2);
How do I solve this and get rid of the 'MinBoxSizes' parameter? Or is there a way to convert the LayerGraph into another type of variable for the training as a workaround?

Answers (2)

Angelo Dumitriu
Angelo Dumitriu on 18 Nov 2018
Edited: Angelo Dumitriu on 18 Nov 2018
I found the problem:
'BoxPyramidScale', 1.2
This must also be removed from the parameters.

Tunai Marques
Tunai Marques on 28 Oct 2019
That does solve the problem because no more scaling is going to be done in the anchors. However, what if you want to use the 'BoxPyramidScale' and 'NumBoxPyramidLevels' parameters? I am interested in having anchors of vastly different sizes, and I am also using lgraph as input. Did you find a solution for that?
Cheers.

Products


Release

R2018b

Community Treasure Hunt

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

Start Hunting!