search

Hon-Wong / PTSEFormer

[ECCV 2022] PTSEFormer: Progressive Temporal-Spatial Enhanced TransFormer Towards Video Object Detection
https://arxiv.org/abs/2209.02242
MIT License
34 stars 7 forks source link

Unable to test or train #4

Closed amnikoo closed 1 year ago

amnikoo commented 2 years ago

Hi, When i run test or train script, i have following error:

conda/miniconda3/envs/PTSEFormer/lib/python3.7/site-packages/torch/distributed/launch.py:186: FutureWarning: The module torch.distributed.launch is deprecated and will be removed in future. Use torchrun. Note that --use_env is set by default in torchrun. If your script expects --local_rank argument to be set, please change it to read from os.environ['LOCAL_RANK'] instead. See https://pytorch.org/docs/stable/distributed.html#launch-utility for further instructions

FutureWarning, Traceback (most recent call last): File "tools/test.py", line 27, in from src.models.model_builder import build_model File "/PTSEFormer/src/models/model_builder.py", line 9, in from .transformer.deformable_transformer import build_deforamble_transformer, build_deformable_encoder, build_deformable_decoder, build_transformer_decoder, SimpleDecoder, SimpleDecoderV2, OursDecoder, OursDecoderV2, OursDecoderV2_exp File "/PTSEFormer/src/models/transformer/deformable_transformer.py", line 20, in from ..ops.modules import MSDeformAttn File "/PTSEFormer/src/models/ops/modules/init.py", line 9, in from .ms_deform_attn import MSDeformAttn File "/PTSEFormer/src/models/ops/modules/ms_deform_attn.py", line 21, in from ..functions import MSDeformAttnFunction File "/PTSEFormer/src/models/ops/functions/init.py", line 9, in from .ms_deform_attn_func import MSDeformAttnFunction File "/PTSEFormer/src/models/ops/functions/ms_deform_attn_func.py", line 18, in import MultiScaleDeformableAttention as MSDA ImportError: /lib64/libstdc++.so.6: version `GLIBCXX_3.4.26' not found (required by /conda/miniconda3/envs/PTSEFormer/lib/python3.7/site-packages/MultiScaleDeformableAttention-1.0-py3.7-linux-x86_64.egg/MultiScaleDeformableAttention.cpython-37m-x86_64-linux-gnu.so) ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 5203) of binary: /conda/miniconda3/envs/PTSEFormer/bin/python Traceback (most recent call last): File "/conda/miniconda3/envs/PTSEFormer/lib/python3.7/runpy.py", line 193, in _run_module_as_main "main", mod_spec) File "/conda/miniconda3/envs/PTSEFormer/lib/python3.7/runpy.py", line 85, in _run_code exec(code, run_globals) File "/conda/miniconda3/envs/PTSEFormer/lib/python3.7/site-packages/torch/distributed/launch.py", line 193, in main() File "/conda/miniconda3/envs/PTSEFormer/lib/python3.7/site-packages/torch/distributed/launch.py", line 189, in main launch(args) File "/conda/miniconda3/envs/PTSEFormer/lib/python3.7/site-packages/torch/distributed/launch.py", line 174, in launch run(args) File "/conda/miniconda3/envs/PTSEFormer/lib/python3.7/site-packages/torch/distributed/run.py", line 713, in run )(*cmd_args) File "/conda/miniconda3/envs/PTSEFormer/lib/python3.7/site-packages/torch/distributed/launcher/api.py", line 131, in call return launch_agent(self._config, self._entrypoint, list(args)) File "/conda/miniconda3/envs/PTSEFormer/lib/python3.7/site-packages/torch/distributed/launcher/api.py", line 261, in launch_agent failures=result.failures, torch.distributed.elastic.multiprocessing.errors.ChildFailedError:

Please help me fix this problem

Hon-Wong commented 1 year ago

Hi,

It seems it is caused by the different versions of pytorch, but I'm not sure about it. I'll keep this issue open until someone else meets the same problem and they solve it.

BW, Han Wang

North1112 commented 1 year ago

Hi, When i run test or train script, i have following error:

conda/miniconda3/envs/PTSEFormer/lib/python3.7/site-packages/torch/distributed/launch.py:186: FutureWarning: The module torch.distributed.launch is deprecated and will be removed in future. Use torchrun. Note that --use_env is set by default in torchrun. If your script expects --local_rank argument to be set, please change it to read from os.environ['LOCAL_RANK'] instead. See https://pytorch.org/docs/stable/distributed.html#launch-utility for further instructions

FutureWarning, Traceback (most recent call last): File "tools/test.py", line 27, in from src.models.model_builder import build_model File "/PTSEFormer/src/models/model_builder.py", line 9, in from .transformer.deformable_transformer import build_deforamble_transformer, build_deformable_encoder, build_deformable_decoder, build_transformer_decoder, SimpleDecoder, SimpleDecoderV2, OursDecoder, OursDecoderV2, OursDecoderV2_exp File "/PTSEFormer/src/models/transformer/deformable_transformer.py", line 20, in from ..ops.modules import MSDeformAttn File "/PTSEFormer/src/models/ops/modules/init.py", line 9, in from .ms_deform_attn import MSDeformAttn File "/PTSEFormer/src/models/ops/modules/ms_deform_attn.py", line 21, in from ..functions import MSDeformAttnFunction File "/PTSEFormer/src/models/ops/functions/init.py", line 9, in from .ms_deform_attn_func import MSDeformAttnFunction File "/PTSEFormer/src/models/ops/functions/ms_deform_attn_func.py", line 18, in import MultiScaleDeformableAttention as MSDA ImportError: /lib64/libstdc++.so.6: version `GLIBCXX_3.4.26' not found (required by /conda/miniconda3/envs/PTSEFormer/lib/python3.7/site-packages/MultiScaleDeformableAttention-1.0-py3.7-linux-x86_64.egg/MultiScaleDeformableAttention.cpython-37m-x86_64-linux-gnu.so) ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 5203) of binary: /conda/miniconda3/envs/PTSEFormer/bin/python Traceback (most recent call last): File "/conda/miniconda3/envs/PTSEFormer/lib/python3.7/runpy.py", line 193, in _run_module_as_main "main", mod_spec) File "/conda/miniconda3/envs/PTSEFormer/lib/python3.7/runpy.py", line 85, in _run_code exec(code, run_globals) File "/conda/miniconda3/envs/PTSEFormer/lib/python3.7/site-packages/torch/distributed/launch.py", line 193, in main() File "/conda/miniconda3/envs/PTSEFormer/lib/python3.7/site-packages/torch/distributed/launch.py", line 189, in main launch(args) File "/conda/miniconda3/envs/PTSEFormer/lib/python3.7/site-packages/torch/distributed/launch.py", line 174, in launch run(args) File "/conda/miniconda3/envs/PTSEFormer/lib/python3.7/site-packages/torch/distributed/run.py", line 713, in run )(*cmd_args) File "/conda/miniconda3/envs/PTSEFormer/lib/python3.7/site-packages/torch/distributed/launcher/api.py", line 131, in call return launch_agent(self._config, self._entrypoint, list(args)) File "/conda/miniconda3/envs/PTSEFormer/lib/python3.7/site-packages/torch/distributed/launcher/api.py", line 261, in launch_agent failures=result.failures, torch.distributed.elastic.multiprocessing.errors.ChildFailedError:

Please help me fix this problem

Excuse me, did you succeed in running