search

doughtmw / HoloLens2-Machine-Learning

Using deep learning models for image classification directly on the HoloLens 2.
MIT License
107 stars 29 forks source link

Detection vs Probablity Threshold #13

Open Avinash0795 opened 2 years ago

Avinash0795 commented 2 years ago

Respected Sir,

Sorry to post with many Questions. I just wanted to know some general Information in coding. What is the difference between Detection Threshold and Probablity Threshold? I tried adapting the codes to my own custom model which had 3 labels/Classes. Upon Detection sometimes I am getting predictions over 100 % and it takes too much of time to give a right Prediction and the probablity keeps changing very rapidly? Sometimes even when I dont look at the desired Image, there is always some Prediction happening rather than being null or no Predictions. I just wanted to know wheter this is all related to Probablity and Detection Thresholds. Are they both the same or different? How to determine an optimal probablity and Detection Thresholds? Please do provide me some Tips if possible.

Thank you.

myarlagadda2022 commented 1 year ago

ction sometimes I am getting predictions over 100 % and it takes too much of time to give a right Prediction and the probablity keeps changing very rapidly? Sometimes even when I dont look at the desired Image, there is always some Prediction happening rather than being null or no Predictions. I just wanted to know wheter this is all related to Probablity and Detection Thresholds. Are they both the same or different? How to determine an optimal probablity and Detection Thresholds? Please do provide m

Hi Avinash Could you please help me out with the setup if possible I am getting Issues