hehefan / pointrnn-pytorch Goto Github PK

Does the pytorch version have complete code including training? If I want to apply it to pytorch, can you provide the complete code.
thank you

Hi @hehefan,
This is an urgent request as I have a deadline to complete a project where I am using your network. I am running the model on nuscenes data and the loss is fluctuating within a certain range and not going down. I have already implemented the range of [-5m, 5m]. Is there any link to a prepared dataset? What else are you using for data preparation? I am using PointLSTM.

Regards.

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 @hehefan,
I am trying to implement this complete architecture of PointRNN using Pytorch and the modules you have provided on the radar points of the nuscenes dataset. There are a few issues. Firstly, my loss values are going very high as I am using Chamfer's distance and Earth Movers distance for my loss as stated in the paper. The loss values are going to more than 100000. I do not know whether this is normal. Then at certain point, the states being returned from the RNN cells are giving very high values in the range of 10 raised to 36. Then, the loss values returned turn out to be Nan values. Any help from you would be highly appreciated as I am working under a deadline.

Thank you.