Li Fuhao

Additionally, if you dont want pytorch version changed, just modify https://github.com/ChanganVR/RelationalGraphLearning/blob/8e87aa5ed8221efd688f8e6857ba4c38637bf6e1/crowd_nav/policy/graph_model.py#L127 to "next_H = next_H + H". And hope @ChanganVR to correct it.

@Vaishnav-B Have you ever solve this error? Thanks.

> > @Vaishnav-B Have you ever solve this error? Thanks. > > @haofuly I haven't been able to solve it yet. @Vaishnav-B I have solved it. The mistake lies in...

> Met similar issue, I worked around it by using https://discuss.pytorch.org/t/runtimeerror-input-type-torch-cuda-floattensor-and-weight-type-torch-halftensor-should-be-the-same/104312/5 > > i.e. adding autocast like > > ``` > from torch.cuda.amp import autocast > with autocast(): > outputs...

> hello, Thank you for your great work. > > I trained "bev_depth_lss_r50_256x704_128x128_24e_2key_ema" of 0.4409 NDS. but, I reproduce only 0.4131 NDS. > > I just changed the batch size...

Hi, @lyfeng001 , I am also wonder the state/action representations. Have you figured it out? Thanks a lot. 1. state/action use delta/absolute eef/joint? 2. Is it meaningful for the extra_delta_transform...

> Hey it should not, as we also do so during training. Hi, @jytime , thus I have a question. I use the padded image (white pixels in the padding...