clovaai / deep-text-recognition-benchmark

Text recognition (optical character recognition) with deep learning methods, ICCV 2019
Apache License 2.0
3.77k stars 1.11k forks source link

[Training] lmdb.Error: The paging file is too small #415

Open HY-Ooi opened 7 months ago

HY-Ooi commented 7 months ago

Hi. I wanna train the model using my own dataset. My train set has 400 samples and validation set has 100 samples. Below are the command and output.

Command

python .\train.py --valid_data Z:\HY\results\Validation --train_data Z:\HY\results\Training --select_data Train --batch_ratio 1 --Transformation None --FeatureExtract VGG --SequenceModeling BiLSTM --Prediction CTC --data_filtering_off --sensitive --workers 0 --workers 0 is used to solve TypeError: can't pickle "Environment' objects https://github.com/clovaai/deep-text-recognition-benchmark/issues/17 , https://github.com/clovaai/deep-text-recognition-benchmark/issues/321

Output

dataset_root: Z:\HY\results\Training opt.select_data: ['Train'] opt.batch_ratio: ['1']

dataset_root: Z:\HY\results\Training dataset: Train sub-directory: /Train num samples: 400 num total samples of Train: 400 x 1.0 (total_data_usage_ratio) = 400 num samples of Train per batch: 192 x 1.0 (batch_ratio) = 192

Total_batch_size: 192 = 192

dataset_root: Z:\HY\results\Validation dataset: / Traceback (most recent call last): File "C:\Users\HY\Desktop\New folder\New folder\deep-text-recognition-benchmark\train.py", line 317, in train(opt) File "C:\Users\HY\Desktop\New folder\New folder\deep-text-recognition-benchmark\train.py", line 35, in train valid_dataset, valid_dataset_log = hierarchical_dataset(root=opt.valid_data, opt=opt) File "C:\Users\HY\Desktop\New folder\New folder\deep-text-recognition-benchmark\dataset.py", line 118, in hierarchical_dataset
dataset = LmdbDataset(dirpath, opt) File "C:\Users\HY\Desktop\New folder\New folder\deep-text-recognition-benchmark\dataset.py", line 135, in init self.env = lmdb.open(root, max_readers=32, readonly=True, lock=False, readahead=False, meminit=False) lmdb.Error: Z:\HY\results\Validation/Validation: The paging file is too small for this operation to complete.