KaiyangZhou
commented
3 years ago it's an error from the pytorch code
a simple google search on "RuntimeError: Couldn't open shared file mapping" should give you useful information https://github.com/pytorch/pytorch/issues/18797 https://github.com/pytorch/pytorch/issues/31874
ww5171351
训练完成后，出现如下警报 => Final test最终试验
Evaluating market1501 (source)
Extracting features from query set ... H:\Code in the paper\deep-person-reid-master\torchreid\metrics\rank.py:12: UserWarning: Cython evaluation (very fast so highly recommended) is unavailable, now use python evaluation.Cython求值（非常快，因此强烈建议）不可用，现在使用python求值。 'Cython evaluation (very fast so highly recommended) is ' H:\Code in the paper\deep-person-reid-master\torchreid\metrics\rank.py:12: UserWarning: Cython evaluation (very fast so highly recommended) is unavailable, now use python evaluation.Cython求值（非常快，因此强烈建议）不可用，现在使用python求值。 'Cython evaluation (very fast so highly recommended) is ' H:\Code in the paper\deep-person-reid-master\torchreid\metrics\rank.py:12: UserWarning: Cython evaluation (very fast so highly recommended) is unavailable, now use python evaluation.Cython求值（非常快，因此强烈建议）不可用，现在使用python求值。 'Cython evaluation (very fast so highly recommended) is ' H:\Code in the paper\deep-person-reid-master\torchreid\metrics\rank.py:12: UserWarning: Cython evaluation (very fast so highly recommended) is unavailable, now use python evaluation.Cython求值（非常快，因此强烈建议）不可用，现在使用python求值。 'Cython evaluation (very fast so highly recommended) is ' Done, obtained 3368-by-512 matrix Extracting features from gallery set ... H:\Code in the paper\deep-person-reid-master\torchreid\metrics\rank.py:12: UserWarning: Cython evaluation (very fast so highly recommended) is unavailable, now use python evaluation.Cython求值（非常快，因此强烈建议）不可用，现在使用python求值。 'Cython evaluation (very fast so highly recommended) is ' H:\Code in the paper\deep-person-reid-master\torchreid\metrics\rank.py:12: UserWarning: Cython evaluation (very fast so highly recommended) is unavailable, now use python evaluation.Cython求值（非常快，因此强烈建议）不可用，现在使用python求值。 'Cython evaluation (very fast so highly recommended) is ' H:\Code in the paper\deep-person-reid-master\torchreid\metrics\rank.py:12: UserWarning: Cython evaluation (very fast so highly recommended) is unavailable, now use python evaluation.Cython求值（非常快，因此强烈建议）不可用，现在使用python求值。 'Cython evaluation (very fast so highly recommended) is ' H:\Code in the paper\deep-person-reid-master\torchreid\metrics\rank.py:12: UserWarning: Cython evaluation (very fast so highly recommended) is unavailable, now use python evaluation.Cython求值（非常快，因此强烈建议）不可用，现在使用python求值。 'Cython evaluation (very fast so highly recommended) is ' Traceback (most recent call last): File "main.py", line 213, in
main()
File "main.py", line 209, in main
engine.run(*engine_run_kwargs(cfg))
File "H:\Code in the paper\deep-person-reid-master\torchreid\engine\engine.py", line 220, in run
ranks=ranks
File "H:\Code in the paper\deep-person-reid-master\torchreid\engine\engine.py", line 335, in test
rerank=rerank
File "F:\Python37\lib\site-packages\torch\autograd\grad_mode.py", line 15, in decorate_context
return func(args, **kwargs)
File "H:\Code in the paper\deep-person-reid-master\torchreid\engine\engine.py", line 384, in _evaluate
gf, g_pids, g_camids = _feature_extraction(gallery_loader)
File "H:\Code in the paper\deep-person-reid-master\torchreid\engine\engine.py", line 363, in _feature_extraction
for batch_idx, data in enumerate(data_loader):
File "F:\Python37\lib\site-packages\torch\utils\data\dataloader.py", line 363, in next
data = self._next_data()
File "F:\Python37\lib\site-packages\torch\utils\data\dataloader.py", line 989, in _next_data
return self._process_data(data)
File "F:\Python37\lib\site-packages\torch\utils\data\dataloader.py", line 1014, in _process_data
data.reraise()
File "F:\Python37\lib\site-packages\torch_utils.py", line 395, in reraise
raise self.exc_type(msg)
RuntimeError: Caught RuntimeError in DataLoader worker process 2.
Original Traceback (most recent call last):
File "F:\Python37\lib\site-packages\torch\utils\data_utils\worker.py", line 185, in _worker_loop
data = fetcher.fetch(index)
File "F:\Python37\lib\site-packages\torch\utils\data_utils\fetch.py", line 47, in fetch
return self.collate_fn(data)
File "F:\Python37\lib\site-packages\torch\utils\data_utils\collate.py", line 74, in default_collate
return {key: default_collate([d[key] for d in batch]) for key in elem}
File "F:\Python37\lib\site-packages\torch\utils\data_utils\collate.py", line 74, in
return {key: default_collate([d[key] for d in batch]) for key in elem}
File "F:\Python37\lib\site-packages\torch\utils\data_utils\collate.py", line 53, in default_collate
storage = elem.storage()._new_shared(numel)
File "F:\Python37\lib\site-packages\torch\storage.py", line 136, in _new_shared
return cls._new_using_filename(size)
RuntimeError: Couldn't open shared file mapping: , error code: <1455>