soeaver/caffe-model

Question about the pspnet

Opened this issue · 1 comments

suzhenghang commented

Hi @soeaver ,
After training the pspnet, could we input a random size image? As the the kernel_size of avepooling is 64, 32, 16 and 8 respectively; If I input the 224x224 image, the feature map of the PSP module will be less the 64.

anqingjianke commented

HI @suzhenghang
Since this code used "sbd_voc2012train_image2category.txt" and "SBD" data. I can not find where to download it and how to transform my image data to “SBD” format.
Could you help me? Thank you.