the orientation of the sequence

[Jacoobr]

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]

This is done in the data itself. In the data files we provide, all polygons are in a fixed orientation.

[Jacoobr]

I got it, thank U~.