Closed zzx332 closed 4 years ago
hi,I have some questions about the code of VTN
pred6 = convolve('pred6', conv6_1, dims, 3, 1) upsamp6to5 = upconvolve('upsamp6to5', pred6, dims, 4, 2, shape5[1:4]) deconv5 = upconvolveLeakyReLU( 'deconv5', conv6_1, shape5[4], 4, 2, shape5[1:4]) concat5 = tf.concat([conv5_1, deconv5, upsamp6to5], 4, 'concat5')
in the VTN code,every upsampling part have pred,this structure is not mentioned in the paper. what is the use of this operation?
It would facilitate deep supervision but we didn't do it so I don't think it makes much difference. VTN should work without them.
hi,I have some questions about the code of VTN
in the VTN code,every upsampling part have pred,this structure is not mentioned in the paper. what is the use of this operation?