How did you measure the accuracy, precision, recall for each dataset?

backseason / PoolNet

Code for our CVPR 2019 paper "A Simple Pooling-Based Design for Real-Time Salient Object Detection"

MIT License

628 stars 153 forks source link

How did you measure the accuracy, precision, recall for each dataset? #68

Open nicnguyen3103 opened 3 years ago

nicnguyen3103 commented 3 years ago

Hi I wonder if you caculate the precision pixel by pixel with the ground truth or did you use another method? Cause I cannot seem to find that information anywhere, I am sorry in advance if I miss it somewhere.

Do you include the function to test for the accuracy in the repo too?

Thank you so much