Low mAP of yolo-tiny-prn.

[ChenCong7375]

I trained yolo-tiny-prn.cfg on VOC dataset with yolo-tiny-conv.13 as pretrain model.
I got 66%mAP on VOC of yolov3-tiny.cfg
But yolov3-tiny-prn.cfg got a lower mAP .
Have you ever trained it on your own dataset?

[AlexeyAB]

What mAP did you get on?

1. yolov3-tiny.cfg
2. yolo-tiny-prn.cfg
3. yolov3-tiny-prn.cfg

[ChenCong7375]

@AlexeyAB
yolov3-tiny.cfg:320320,66%mAP
yolov3-tiny-prn.cfg:320320,60%mAP

[AlexeyAB]

How many iterations did you train both cfg-files?

[ChenCong7375]

50000 iterations，for 20 classes in VOC dataset

[WongKinYiu]

i think the reason is that u use the coco pretrained model on yolo-v3-tiny instead of yolo-v3-tiny-prn.
i use prn.conv.15 instead of tiny.conv.13, and the results are as follows:

[ChenCong7375]

@WongKinYiu thanks very much for your repo.

[ChenCong7375]

@WongKinYiu So you used prn.conv.15 and get 64% mAP?
But I got 68% mAP… so can you share your chart?

[ChenCong7375]

@WongKinYiu

[WongKinYiu]

i do not save the chart.
and i trained the model in march, there are so many improvement of this repo in these days.

however, 68% mAP is better than 64%, it is a good news.

[samohadid]

hi @WongKinYiu
can you give me a link to download prn.conv.15 pre-trained model ?
thank you very much

[developer0hye]

@WongKinYiu

Thank you for experiments!

I have two quesetions.

1. What does W/O COCO model mean?

training from imagenet pretrained model? or training from scratch?

2. Normalization method for preprocessing

Did you normalize the input image by mean and std value?

If you did, what do you use mean and std from imagenet or voc dataset?

[WongKinYiu]

What does W/O COCO model mean?

w\o = without, without coco pretrain.

training from imagenet pretrained model? or training from scratch?

from imagenet pretrain

Normalization method for preprocessing

/255.

[developer0hye]

@WongKinYiu
Thanks!

[developer0hye]

@WongKinYiu

I have new two question.

1. How do you normalize image to train the model on Imagenet?

same with /255.?

2. What resize method do you use for preprocessing?
   Resizing : keeping aspect ratio, or not #232 (comment)