Why didn't fasterRCNNLayers implement alternating training?

2024 2 8
1 个回答
回答已采纳
更新时间：2024 2 17
11 次查看（30 天）

1 个投票

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?

请先登录，再回答此问题。

 采纳的回答

Angelo Yeo
Angelo Yeo 2024-2-17

0 个投票

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.

更多回答（0 个）

类别

在 帮助中心 和 File Exchange 中查找有关 Instance Segmentation 的更多信息

产品

标签

Community Treasure Hunt

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

Start Hunting!

Translated by