CerrieJ
CerrieJ
How do you get the ground truth matches data —— "ed_GroundTruthMatches.txt" and "lsd_GroundTruthMatches.txt"?
### Question 跑训练过程遇到 pos_embed算子输入的shape不匹配，请教大概是什么原因呢？我是pt2.3，其他以来版本是requirments.txt中内容 [rank5]: File "/torch/venv3/pytorch/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl [rank5]: return forward_call(*args, **kwargs) [rank5]: File "/gpfs/xj/Salience-DETR_mlu/models/bricks/salience_transformer.py", line 565, in forward [rank5]: query_with_pos = key_with_pos = self.with_pos_embed(query, query_pos) [rank5]:...
I got an error: FileNotFoundError: [Errno 2] No such file or directory: 'data/nuscenes/bevdetv2-nuscenes_infos_train.pkl' 479 def default_drivelm(self, ann_paths): 480 self.annotation = json.load(open(ann_paths[0], "r")) 481 self.data_info = pickle.load(open("data/nuscenes/bevdetv2-nuscenes_infos_val.pkl", "rb"))["infos"] How to get...
1. can I use the nuScenes-v1.0-mini for trainning? 2. 'For a quick verification of the pipeline, we recommend downloading the subset dataset of [DriveLM](https://github.com/OpenDriveLab/DriveLM/blob/main/docs/data_prep_nus.md) and organizing the data in line...