Open timlueg opened 6 years ago
I also found this problem. This is caused by the difference of the Max-Pooling Layer in Caffe and Draknet. The darknet will set the pad = 1 in the Max-Pooling layer when you did not give a pad value.
I tried adding pad = 1 to all maxpool layers in yolov3-tiny.cfg file as well as modifying the darknet2caffe script to generate the padding for the .prototxt file but there is still a shape mismatch.
I think this problem happens because the padding mode in caffe don't support SAME. The last maxpool has an input size of 13x13, filter size is 2, stride is 1. So it has an output size of 12x12 without SAME mode as 13 is odd. I wonder how to solve this in caffe @BingzheWu
So did you guys have had an solution for this now ? I run to the same issue now.
@BingzheWu @comeonwmz
You can try adjusting the filter size of the maxpool to make it pass. e.g. size is 3 &pad is 1, or size is 1 while pad is 0. I don't know if there is any other way to solve the problem @chenyuqing
Converting yolov3-tiny model with darknet2caffe.py results in the following error.
yolov3-tiny.cfg.txt full_log.txt