OpenPCDet

OpenPCDet copied to clipboard

These commits just represent some refactoring I did in order to easily introduce the loading of laser origins. I will link the follow-up PR here after creation, which explains why...

demmerichs

Improving experiment configuration

4

This PR is addressing #1278. I use this myself and be happy to address any problems or issues. If this kind of change is not wanted, please let me know...

demmerichs

convert np.bool to np.bool_

1

When I train pointpillar_pyramid_aug, the error occurs. ```python AttributeError: module 'numpy' has no attribute 'bool'. `np.bool` was a deprecated alias for the builtin `bool`. To avoid this error in existing...

zhangtingyu11

erro: scores, dt_box_lidar, types, pred_dict = proc_1.run(np_p, frame)

1

length of proc_1.run(np_p, frame) is 10 :   how should I modify, thanks~

mendoza-G

Previous code attempted to generate for all type of data inside splits list(which has ["train", "val", "test", "raw_small", "raw_medium", "raw_large"]). It occurs error even if just one split doesn't exist...

kun-woo-park

[Training Scripts] Distributed Training Script Python Argument Incorrect.

1

When running the command ```sh scripts/dist_train.sh 4 --cfg_file ...``` I get the following error. ``` further instructions warnings.warn( [2024-04-22 13:22:53,028] torch.distributed.run: [WARNING] [2024-04-22 13:22:53,028] torch.distributed.run: [WARNING] ***************************************** [2024-04-22 13:22:53,028] torch.distributed.run:...

tjtanaa

File "/home/admin1/anaconda3/envs/plmee/lib/python3.8/site-packages/allennlp/data/token_indexers/wordpiece_indexer.py", line 345, in __init__ super().__init__(vocab=bert_tokenizer.vocab, AttributeError: 'NoneType' object has no attribute 'vocab'

1

python src/extractor_trainer.py --pretrained_bert /data/wangx/models/chinese_roberta_wwm_ext_large --bert_vocab /data/wangx/models/chinese_roberta_wwm_ext_large/vocab.txt --do_train_trigger --data_meta_dir ./data/DuEE --extractor_origin_trigger_dir ./save/DuEE/bert_large/trigger --extractor_origin_role_dir ./save/DuEE/bert_large/role --extractor_epoc 20 --extractor_batch_size 12 --extractor_train_file ./data/DuEE/train.json --extractor_val_file ./data/DuEE/dev.json Model name '/data/wangx/models/chinese_roberta_wwm_ext_large/vocab.txt' was not found in model name...

SnowS13

FileNotFoundError: [Errno 2] No such file or directory: 'cfgs/dataset_configs/kitti_dataset.yaml'

1

I use vscode to debug OpenPCDet, and found second.yaml file include relative path, so vscode can't find the configure file if the work diretory is set and ``` OpenPCDet ├──...

hitbuyi

Low Acc on 3D task, in Custom datasets.

1

Thank you for your excellent work. I'm trying to use OpenPCDet's customized dataset feature, but I'm finding that my models are performing particularly poorly for BEV and 3D tasks, does...

Mike-7777777

I can train the model, but when it comes to testing or evaluating it, I encounter the error message: 'RuntimeError: CUDA error: no kernel image is available for execution on the device.'

3

I run on Tesla P100. Environment - torch 1.8.1+cu111 - python 3.8 - cuda 11.1 When running **train.py**, I encountered an error. It appears that training has completed successfully, but...

cgoldbird