Closed Almo1982 closed 7 years ago
Hey Stefan,
When writing the SegNet papers I was using the matlab script here: https://github.com/alexgkendall/SegNet-Tutorial/blob/master/Scripts/compute_test_results.m
However a direct evaluation in python would make more sense!
Alex
Hi Alex,
thank you for your Feedback!
Yes, in the meantime i realized this matlab-script and i was already able to run it with my own predictions of a custom dataset.
I will close this issue then.
Thanks! Stefan
Hi Alex,
thank you for your Feedback!
Yes, in the meantime i realized this matlab-script and i was already able to run it with my own predictions of a custom dataset.
I will close this issue then.
Thanks! Stefan
Can you pls provide the Python code???
hey I trained segnet on camvid dataset, and got the acc by Scripts/compute_test_results.m. The global acc is great(>0.9), but the other acc is too low( about 0.15), I don't know the reason about it, Can you help me? thanks.
Hi all,
i trained a couple of SegNet Nets so far, everything works fine testing my models with the test_segmentation.py file that shows me the results visually. I am wondering how i can calculate the Global, Class an Mean I/U accuracy values like shown in the table of the results in the tutorial? I know the formula for this with the TP, TN, FP and FN meanings, but do i have to write a script by myself or is there anything coming with SegNet i didnt recognize so far?
Thank you! Stefan