Transfer Learning using deepNetwork Designer to show Precision and Recall, F1 score, Mean Average Precision and Mean Absolute Error.

I have tried to use deepNetwork Designer to perform Transfer Learning and have used Darknet53 network. Then I set my images (already preprocessed images of Person) to be the Data. After setting the Training Options, I proceeded to Training. I can see the on the results the Accuracy, Loss, and other info. However, I want to know if it's possible to also show the Precision and Recall, F1 Score, Mean Average Precision? I am trying to find detailed documentations and would love to hear from other experts here. I am still exploring Experiment Manager if it's possible there but am hoping somebody here who has a commendable idea on how to do these? Thank you so much.

Answer 1

[Venu]

Hi @Hanes Ongos

This MATLAB answer might help you.

https://www.mathworks.com/support/search.html/answers/663943-deep-network-designer-pretrained-network.html?fq%5B%5D=asset_type_name:answer&fq%5B%5D=category:deeplearning/image-data-workflows&page=1