Why didn't fasterRCNNLayers implement alternating training?

Why didn't fasterRCNNLayers implement alternating training?

I ran this script. (Object Detection Using Faster R-CNN Deep Learning)

I wanted to take a closer look at this layer(fasterRCNNLayers) by entering the following code[deepNetworkDesigner(lgraph)].

However, unlike what is in the paper(Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks), this layer did not implement alternating training.

Why is it not implemented?

Answer 1

[Angelo Yeo]

As far as I can understand, you probably have meant "alternating training" as the four steps in the paper, i.e.,

1. train the RPN, then freeze RPN layers,
2. train RCNN, then freeze RCNN layers,
3. train RPN, then freeze RPN layers
4. train RCNN.

It is implemented in Computer Vision Toolbox! You can do this by changing TrainingMethod to 'four-step' if you change the training method of trainFasterRCNNObjectDetector. See the document for detailed explanation for this option.