How to assess overfitting in training faster r-cnn by the "trainFasterRCNNObjectDetector" function, which can not set validation data.
2 visualizaciones (últimos 30 días)
Mostrar comentarios más antiguos
Hi,
I want to use the "trainFasterRCNNObjectDetector" function to train a object detector, but in the options of the "trainFasterRCNNObjectDetector" note:
trainFasterRCNNObjectDetector does not support these training options:
- The Plots value: 'training-progress'
- The ValidationData, ValidationFrequency, or ValidationPatience options
- The OutputFcn option.
Thus, how to assess when our network is overfitting without using the validation set?
0 comentarios
Respuestas (0)
Ver también
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!