Is there any wrong with eval_iou()?
Hi, thx for your nice work! When I train the model, I find a problem. In train dataset, IOU can achieve about[0.8 0.6 0.8], while its eval IOU is only about [0.04 0.01 0.05]. Here it is:
So Is there any wrong with function eval_iou()? It seems to be an order of magnitude smaller. Thanks for your time.
+1 question
+1
Have you solved this problem yet?
Hi. What do the three numbers in IOU list mean? Thanks
Correspond one-to-one with the class list
Correspond one-to-one with the class list
Thanks for your answer. I want to check the order: Divider, Crossing, Boundary.
Is that correct? Many Thanks.