-
Notifications
You must be signed in to change notification settings - Fork 7.9k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
why my mAP is close to 1? #808
Comments
I modify the line ‘npos = npos + sum(~difficult)’ to ‘npos = npos + len(R)’,then the code runs well,but I still don't if this code is right..Because my mAP is 0.611 which is a little lower than my expectation.... |
mAP = 0.98 is very well, it means that mAP = 98%.
|
So your currently mAP = 60.27% IoU during training ( How many iterations did you train? |
But the pictures in my dataset are 1242 X 375. |
And train Yolo v3 from the begining. |
But it will work 2.7x times slower. If Out of memory error will occur, then increase subdivison=16, 32 or 64. |
How many iterations did you train? Or did you just set these param and do Try to train from the begining using these params - you should get higher mAP. |
|
So do I need to change the anchors ?Because now the grid in the last feature map is not 13 X 13 anymore,but 39 X 12.And if I need to change,how? |
Use this command: https://github.com/AlexeyAB/darknet#how-to-improve-object-detection And change anchors in each of 3 [yolo] layers. |
So,if I want to change the backbone of darknet,which files do I need to modify? |
Modify your cfg-file.
Recalculate anchors and then in each of 3
For example you want to use 3 anchors instead of 9, then:
|
Hello @AlexeyAB, Will the number of anchor boxes, increase or decrease performance or accuracy. In my case, I am just trying to detect license plates (which normally have the same aspect ratio, but in different sizes). I am using a modified version of tiny-yolo now, with 6 anchors instead of 9. Thank you |
@marcunzueta Hi, Try to calculate 8 or 10 anchors for your dataset with flag |
@gooodooo train more than 2000 iterations |
hi,thank you very much . |
@gooodooo Use yolov3.cfg and increase |
HI,I read the paper about YOLOv3,but it doesn't mention the mAP performance on PASCAL VOC dataset.Can you share the mAP of darknet53-416 on PASCAL VOC?Because I want to compare my results to the standard result(especially darknet53-416)! |
@ShoufaChen I have not found yet |
@ShoufaChen There is no mAP for Pascal VOC on Yolo v3. You should train and check it by yourself. |
@AlexeyAB ok, thank you. |
I use YOLOv3 to training on my own dataset which only contains 3 kinds of objects.And I delete the 'difficult' information which I don't if it is the reason to cause this warning.Because
npos = 0
and I delete "npos = npos + sum(~difficult)"
in the end : rec = tp / float(npos)
So I think the missing of "difficult" is the reason to cause the runtime warning.
But my dataset is KITTI which dosen't contain the "difficult" information.
So how can I avoid this error since I think the mAP is wrong.
The text was updated successfully, but these errors were encountered: