-
Notifications
You must be signed in to change notification settings - Fork 1.5k
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
Did you check accuracy of YOLOv4 by using your implementation on MSCOCO? #190
Comments
+1 |
1 similar comment
+1 |
This is result on COCO validation set (val2017), input is 416*416.
This is result from AlexeyAB/darknet#5354
|
|
Pretrained DarkNet weights were used to generate pth. |
@ersheng-ai Try to use resizing without keeping-aspect-ratio/padding-zeros, will accuracy be better? |
I will try it |
Zero padding is removed so that images of any ratio are squashed or stretched to 416 * 416
|
So there is no big drop in accuracy. Great! Do you use padding = SAME or VALID for conv and maxpooling(in SPP-block) in YOLOv4? |
I think the Pytorch model strictly follows the routines. |
Hi,@ersheng-ai. Thank you for your great job! And I have a question! This project seems to only use yolov4' network and mosaic, but donot use Eliminate grid sensitivity,IoU threshold, CIOU loss and so on. This project get 46.6% AP while darknet yolov4 only get 47.1% AP in coco val-2017. So what matters most in getting AP as high as darknet ? |
How the performance obtained, train from cspdarknet imagenet pretrained model or yolov4 coco pretrained model? |
why pyorch visin should use conf_thresh = 0.001 to compute mAP? |
Hi,@ersheng-ai. Thank you for your great job! I have one question: |
Is there any code to reproduce this mAP? |
@ersheng-ai How do I run validation on coco ? |
How to evaluate, can you provide the command? |
What files did you use and what commands did you use to implement your evaluation? Any other changes from the original gituhub code would be appreciated. |
@Tianxiaomo Hi,
Did you check accuracy of YOLOv4 by using your implementation, do you get the same 43.5% AP (65.7% AP50) for yolov4.cfg 608x608 on MS COCO testdev?
Did you check, do you get the same detection result by using Darknet implementation and your implementation by using converted model?
for example for this image:
The text was updated successfully, but these errors were encountered: