the orientation of the sequence
Jacoobr opened this issue · 2 comments
Jacoobr commented
Hi, @amlankar , I don't understant that you said in your paper CVPR17: "Here, we fix the polygon to always follow the clockwise orientation,".But how you did it in your code?, In other words, How can you control the orientation to be clockwise always? I looked into the rnn_step
with attention
mechanism of your code like :
att_feats, att = self.attention(feats, rnn_state)
att_feats_bak, att_bak = self.attention(feats, rnn_state_back)
input_t = torch.cat((att_feats, v_prev2, v_prev1, v_first), dim=1)
Does the 'catination' order of 'v_prev2, v_prev2, v_first' make clockwise orientation? Apprecaitive for your reply, thank U~.
amlankar commented
This is done in the data itself. In the data files we provide, all polygons are in a fixed orientation.
Jacoobr commented
I got it, thank U~.