YOLOv3_PyTorch icon indicating copy to clipboard operation
YOLOv3_PyTorch copied to clipboard

Published 20 hours ago • verified publisher icon BobLiu20

Hi,I have some problem to trained voc2007 dataset!!!

Open BCWang93 opened this issue 5 years ago • 7 comments

When I use the code to train the voc2007 dataset,I get the result as follows: 1 2 3 4 5 6 7 8 And the detected result is none!Anyone can help me ?Thanks!

BCWang93 avatar Apr 07 '19 01:04 BCWang93

I trained the VOC2012 dataset, and everything just looks fine for me. Screenshot Did you change the class number from 80 to 20? Or you should give more details.

AndrewZhuZJU avatar Apr 17 '19 03:04 AndrewZhuZJU

I trained the VOC2012 dataset, and everything just looks fine for me. Screenshot Did you change the class number from 80 to 20? Or you should give more details.

Thanks for your reply! Did you use the origin code? or you have some change?I have changed the class number from 80 to 20.But I get this result in voc2007.

BCWang93 avatar Apr 17 '19 04:04 BCWang93

I trained the VOC2012 dataset, and everything just looks fine for me. Screenshot Did you change the class number from 80 to 20? Or you should give more details.

Hi,can you see the loss_x and loss_y,loss_w,loss_h?it is convergence？Btw,you use the origin code? Did you changed something?

BCWang93 avatar Apr 17 '19 07:04 BCWang93

I trained the VOC2012 dataset, and everything just looks fine for me. Screenshot Did you change the class number from 80 to 20? Or you should give more details.

Can you detect the bbox use the model of you trained?When I test the trained model use image,the ouput is none,it can't detected anything!Thanks!

BCWang93 avatar Apr 17 '19 08:04 BCWang93

I trained the VOC2012 dataset, and everything just looks fine for me. Screenshot Did you change the class number from 80 to 20? Or you should give more details.

Can you detect the bbox use the model of you trained?When I test the trained model use image,the ouput is none,it can't detected anything!Thanks!

No need to change the code. The reason for nothing detected is NMS removes all your predicted bounding box, which means your model is not trained well.

AndrewZhuZJU avatar Apr 17 '19 10:04 AndrewZhuZJU

I trained the VOC2012 dataset, and everything just looks fine for me. Screenshot Did you change the class number from 80 to 20? Or you should give more details.

Can you detect the bbox use the model of you trained?When I test the trained model use image,the ouput is none,it can't detected anything!Thanks!

No need to change the code. The reason for nothing detected is NMS removes all your predicted bounding box, which means your model is not trained well.

OK，I don't change the code.but the result I get is not well like you.I don't know the reason is what? This trouble me some days! Did you use the data_agumentent.py keepAspect in this code?Thanks!

BCWang93 avatar Apr 17 '19 10:04 BCWang93

@BCWang93 @AndrewZhuZJU i think both of you have used VOC2007? did you have use coco_person_keypoints_train_2017?

eng100200 avatar Jun 02 '20 06:06 eng100200