GitLab

support merge_all_iters_to_one_epoch to avoid deadlock when switching epochs, eval last 10 epochs after training

support more flexible setting of conv head; slice inputs when batch size is too large in PFNLayer to avoid bugs (#124)

* support more flexible setting

* slice inputs of nn.Linear when batch size is too large

bugfixed: velocity in infos with official nuscenes-devikit, add FILTER_MIN_POINTS_IN_GT config for nuscenes dataset

* remove warning from yaml and dbsampler

* bugfixed: support gt_sampling with empty scenes, add logger without log_file

* abstract load_data_to_gpu function in train/test

* add comments for supporting costum dataset