deep-text-recognition-benchmark icon indicating copy to clipboard operation
deep-text-recognition-benchmark copied to clipboard

Published 20 hours ago • verified publisher icon clovaai

Training my dataset

Open farshokat opened this issue 3 years ago • 1 comments

Hi, t using create_lmdb_dataset.py done, I have data.mdb and lock.mdb but when i using this file .mdb to training, I have error is: 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: /content/drive/MyDrive/Data_STR_OCR/Train opt.select_data: ['/content/drive/MyDrive/Data_STR_OCR/Result'] opt.batch_ratio: ['0.5', '0.5']

I using google colab to training and my dataset is plate car in Viet Nam. i don't know why? Please me, thanks.

farshokat avatar Jun 18 '21 04:06 farshokat

Hi,

I think it already been answered by https://github.com/clovaai/deep-text-recognition-benchmark/issues/85#issuecomment-538849843 already.

allenwu5 avatar Oct 21 '21 08:10 allenwu5