Hi,
I am implementing the pytorch version of Pointlstm for nuscenes data. I have a question regarding the encoder decoder structure. As mentioned in the architecture, the state from the encoder is supposed to be used in the decoder. But looking at the code, I am unable to find out where that is happening as I see the state from the last encoder cell, states3 is not being used anywhere in the decoder cells.
Thank you.
Hi, I am implementing the pytorch version of Pointlstm for nuscenes data. I have a question regarding the encoder decoder structure. As mentioned in the architecture, the state from the encoder is supposed to be used in the decoder. But looking at the code, I am unable to find out where that is happening as I see the state from the last encoder cell, states3 is not being used anywhere in the decoder cells. Thank you.