Open GMXela opened 2 years ago
I have the same problem.
That sounds to be related to PyTorch. Adding --workers 0
fixed the problem for me. Check this issue.
That sounds to be related to PyTorch. Adding
--workers 0
fixed the problem for me. Check this issue.
thanks, it works!
Hello,
I have this error and I really don't know what to do. I'm new in coding so, I really need help! :-P
there is all lines in my Terminal : (THX for helping me)
PS C:\Users\guit_\PycharmProjects\Text Recognition\deep-text-recognition-benchmark-master> python train.py --train_data data_lmdb_release/training --valid_data data_lmdb_release/validation --select_data MJ-ST --batch_ratio 0.5-0.5 --Transformation None --FeatureExtraction ResNet --SequenceModeling BiLSTM --Prediction CTC Filtering the images containing characters which are not in opt.character Filtering the images whose label is longer than opt.batch_max_length
dataset_root: data_lmdb_release/training opt.select_data: ['MJ', 'ST'] opt.batch_ratio: ['0.5', '0.5']
dataset_root: data_lmdb_release/training dataset: MJ sub-directory: /MJ\MJ_test num samples: 891924 sub-directory: /MJ\MJ_train num samples: 7224586 sub-directory: /MJ\MJ_valid num samples: 802731 num total samples of MJ: 8919241 x 1.0 (total_data_usage_ratio) = 8919241 num samples of MJ per batch: 192 x 0.5 (batch_ratio) = 96 Traceback (most recent call last): File "train.py", line 317, in
train(opt)
File "train.py", line 31, in train
train_dataset = Batch_BalancedDataset(opt)
File "C:\Users\guit\PycharmProjects\Text Recognition\deep-text-recognition-benchmark-master\dataset.py", line 69, in init
self.dataloader_iter_list.append(iter(_dataloader))
File "C:\Users\guit.conda\envs\Benchmark_env\lib\site-packages\torch\utils\data\dataloader.py", line 359, in iter
return self._getiterator()
File "C:\Users\guit.conda\envs\Benchmark_env\lib\site-packages\torch\utils\data\dataloader.py", line 305, in _get_iterator
return MultiProcessingDataLoaderIter(self)
File "C:\Users\guit.conda\envs\Benchmarkenv\lib\site-packages\torch\utils\data\dataloader.py", line 918, in init
w.start()
File "C:\Users\guit.conda\envs\Benchmark_env\lib\multiprocessing\process.py", line 121, in start
self._popen = self.Popen(self)
File "C:\Users\guit.conda\envs\Benchmark_env\lib\multiprocessing\context.py", line 224, in _Popen
return _default_context.get_context().Process._Popen(processobj)
File "C:\Users\guit.conda\envs\Benchmark_env\lib\multiprocessing\context.py", line 327, in _Popen
return Popen(processobj)
File "C:\Users\guit.conda\envs\Benchmark_env\lib\multiprocessing\popen_spawn_win32.py", line 93, in init
reduction.dump(process_obj, tochild)
File "C:\Users\guit.conda\envs\Benchmarkenv\lib\multiprocessing\reduction.py", line 60, in dump
ForkingPickler(file, protocol).dump(obj)
TypeError: cannot pickle 'Environment' object
PS C:\Users\guit\PycharmProjects\Text Recognition\deep-text-recognition-benchmark-master> Traceback (most recent call last):
File "", line 1, in
File "C:\Users\guit_.conda\envs\Benchmark_env\lib\multiprocessing\spawn.py", line 116, in spawn_main
exitcode = _main(fd, parentsentinel)
File "C:\Users\guit.conda\envs\Benchmark_env\lib\multiprocessing\spawn.py", line 126, in _main
self = reduction.pickle.load(from_parent)
EOFError: Ran out of input