- train the RPN, then freeze RPN layers,
- train RCNN, then freeze RCNN layers,
- train RPN, then freeze RPN layers
- train RCNN.
Why didn't fasterRCNNLayers implement alternating training?
1 visualización (últimos 30 días)
Mostrar comentarios más antiguos
지현
el 8 de Feb. de 2024
Respondida: Angelo Yeo
el 17 de Feb. de 2024
Why didn't fasterRCNNLayers implement alternating training?
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?
0 comentarios
Respuesta aceptada
Angelo Yeo
el 17 de Feb. de 2024
As far as I can understand, you probably have meant "alternating training" as the four steps in the paper, i.e.,
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.
0 comentarios
Más respuestas (0)
Ver también
Categorías
Más información sobre Image Data Workflows en Help Center y File Exchange.
Productos
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!