search

ZikangZhou / HiVT

[CVPR 2022] HiVT: Hierarchical Vector Transformer for Multi-Agent Motion Prediction
https://openaccess.thecvf.com/content/CVPR2022/papers/Zhou_HiVT_Hierarchical_Vector_Transformer_for_Multi-Agent_Motion_Prediction_CVPR_2022_paper.pdf
Apache License 2.0
577 stars 115 forks source link

Friendly Remind #4

Closed XM-WANG closed 2 years ago

XM-WANG commented 2 years ago

I met some errors following the environment configuration.

conda install pytorch==1.8.1 cudatoolkit=11.3 -c pytorch -c conda-forge
conda install pytorch-geometric==1.7.2 -c rusty1s -c conda-forge
conda install pytorch-lightning=1.5.2 -c conda-forge

will install the torch with CPU version in default.

XM-WANG commented 2 years ago

Here is the error:

(HiVT) bash-4.2$ python train.py --root datasets/ --embed_dim 64 Global seed set to 2022 Traceback (most recent call last): File "train.py", line 41, in trainer = pl.Trainer.from_argparse_args(args, callbacks=[model_checkpoint]) File "/misc/kfdata01/kf_grp/zzwang/anaconda3/envs/HiVT/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 1936$ in from_argparse_args return from_argparse_args(cls, args, kwargs) File "/misc/kfdata01/kf_grp/zzwang/anaconda3/envs/HiVT/lib/python3.8/site-packages/pytorch_lightning/utilities/argparse.py", line 6$ , in from_argparse_args return cls(trainer_kwargs) File "/misc/kfdata01/kf_grp/zzwang/anaconda3/envs/HiVT/lib/python3.8/site-packages/pytorch_lightning/trainer/connectors/env_vars_co$ nector.py", line 38, in insert_env_defaults return fn(self, **kwargs) File "/misc/kfdata01/kf_grp/zzwang/anaconda3/envs/HiVT/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 426, in init gpu_ids, tpu_cores = self._parse_devices(gpus, auto_select_gpus, tpu_cores) File "/misc/kfdata01/kf_grp/zzwang/anaconda3/envs/HiVT/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 1538$ in _parse_devices gpu_ids = device_parser.parse_gpu_ids(gpus) File "/misc/kfdata01/kf_grp/zzwang/anaconda3/envs/HiVT/lib/python3.8/site-packages/pytorch_lightning/utilities/device_parser.py", l$ ne 89, in parse_gpu_ids return _sanitize_gpu_ids(gpus) File "/misc/kfdata01/kf_grp/zzwang/anaconda3/envs/HiVT/lib/python3.8/site-packages/pytorch_lightning/utilities/device_parser.py", l$ ne 151, in _sanitize_gpu_ids raise MisconfigurationException( pytorch_lightning.utilities.exceptions.MisconfigurationException: You requested GPUs: [0] But your machine only has: []

XM-WANG commented 2 years ago

image It is because the torch cannot find the GPU device. I re-installed torch and fix this error.

ZikangZhou commented 2 years ago

Thanks a lot! It seems that cuda-version Pytorch 1.8.1 cannot be downloaded correctly. Pytorch 1.8.0 seems to work well.