Open ghost opened 6 years ago
Try to use yolov3.conv.81
where can i get the yolov3.conv.81 or yolov3.conv.105?I only find darknet53.conv.74. thanks.
@baolinhu
Download file: https://pjreddie.com/media/files/yolov3.weights
How to get file yolov3.conv.81
https://github.com/AlexeyAB/darknet/blob/eff487ba3626a39e135d13929117e04bc4cf5823/build/darknet/x64/partial.cmd#L21
What is the difference between yolov3.conv.105 and yolov3.conv.81.Thanks.
@lvshuaigg
darknet53.conv.74
takes 74 layers from darknet53.weights
yolov3.conv.105
takes 105 layers from yolov3.weigths
yolov3.conv.81
takes 81 layers [0 - 80] - this is correct pre-trained weights.yolov3.conv.105 is incorrect - because layer-81 depends on number of classes, so higher layers will be shifted if number of classes will be changed.
Thank you very much.
@lvshuaigg You can use any of them: yolov3.conv.81 (is Trained on MS COCO) or darknet53.conv.74 (is trained on Imagenet)
darknet53.conv.74
takes 74 layers from darknet53.weights
yolov3.conv.81
takes 81 layers from yolov3.weigths
@AlexeyAB , Can I use darknet53.conv.74 for 832 x 480 aspect ratio? If darknet53.conv.74 is obtained from imagenet (I understand the image aspect ratio here is mostly 1:1) / Pascal VOC data, does it reduce the accuracy when I train the custom images of 832 x 480 aspect?
@kmsravindra Yes, you can. darknet53 is trained with crop-data-augmentation (like jitter in the Yolo): https://github.com/AlexeyAB/darknet/blob/21a4ec9390b61c0baa7ef72e72e59fa143daba4c/cfg/darknet53.cfg#L13-L14 So it is slightly invariant to aspect ratio.
I think it will be better to use darknet53.conv.74 than not to use darknet53.conv.74 in your case.
Thanks for your reply @AlexeyAB.
I am trying to learn the 2 class problem. One is person and the other is a minor class which is neither in imagenet nor coco.
In yolov3, I know the following three pre-trained models, Which do you think is the best in this case? The reason for this is also?
yolov3.conv.105 yolov3.conv.81 darknet53.conv.74