option training progress plot for RCNN Detector

14 ビュー (過去 30 日間)
Abdussalam Elhanashi
Abdussalam Elhanashi 2019 年 9 月 14 日
回答済み: Raunak Gupta 2019 年 9 月 17 日
Hi Guys
I am looking if threre is anyway for getting the plot of training progress for RCNN Detector
I have checked Matlab and as per the link below but it does not support the plot training progress for RCNN
Note
trainRCNNObjectDetector does not support these training options:
  • The Plots value: 'training-progress'
  • The ValidationData, ValidationFrequency, or ValidationPatience options
  • The OutputFcn option.
Thanks

採用された回答

Raunak Gupta
Raunak Gupta 2019 年 9 月 17 日
Hi,
The specific ‘training-progress’ is not available for ‘Plots’ Property for trainRCNNObjectDetector. I would suggest you to save the info that contains the information about training loss and accuracy after each iteration by using
[detector,info] = trainRCNNObjectDetector(___)
This info object will return Training Loss, Training Accuracy and Learning Rate for each epoch in a structure which you may access later for plotting the result for visualization. Dynamically visualizing the training progress on a plot is not supported. By this way you can see the training progress after the training finishes.
For Other factors in RCNN Detector Training please take a look at the Training Options.

その他の回答 (0 件)

Community Treasure Hunt

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

Start Hunting!

Translated by