Yuan Wu

inconsistency between the performance of github

1

Hi , when I test the config of **flashocc-r50-4d-stereo**, the result is 38.07 : ``` ===> per class IoU of 6019 samples: ===> others - IoU = 9.37 ===> barrier...

Question about using 1 gpu to train/eval

2

Hi, thanks for sharing this great project. Is there a way to use 1 gpu to train or eval the model? I encouted RuntimeError as blow. I have tried to...

Hi，why do we need to apply DeformableAttnFunction on depth first？ https://github.com/NVlabs/FB-BEV/blob/832bd81866823a913a4c69552e1ca61ae34ac211/mmdet3d/models/fbbev/view_transformation/backward_projection/bevformer_utils/spatial_cross_attention_depth.py#L452-L454

Hi, thanks for sharing this great project! The model link in the readme file seems broken. May I ask where can I download the model weight?

Hi, thanks for sharing this great project! If I want to use one history frame for temporal fusion. Do I only need to change num_memory->1 in config file? ``` num_memory...