search

yun-liu / RCF

Richer Convolutional Features for Edge Detection
Other
752 stars 259 forks source link

Why the up sample size is 8 in the last stage? #75

Closed xianshunw closed 5 years ago

xianshunw commented 5 years ago

https://github.com/yun-liu/rcf/blob/cd007aca3bd6a908d9df2213fb62966606bb7bfa/examples/rcf/train_val.prototxt#L214

The feature map size of the conv_5 is 1/16 of the input image size, so I think the kernel size should be 32 and the stride should be 16.

xianshunw commented 5 years ago

Oh, sorry to disturb you. I did study your code carefully.