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

Error While Training Custom Dataset #299

Closed ctcheune closed 3 years ago

ctcheune commented 3 years ago

I ran the create_lmdb_dataset.py script and successfully created the data.mbd and lock.mbd and put them into the data_lmbd_release/training directory. But when I ran the train.py script, I got the following error:

AssertionError: datasets should not be an empty ot be an empty iterable' # type: ignor iterable

Am I supposed to split my data beforehand into evaluation, training and validation sets and then run the create_lmdb_dataset.py script on each of them?

Thanks for your help!

ctcheune commented 3 years ago

Solved!

lyc728 commented 2 years ago

Solved! hello how did you sovle it ?

wjbmattingly commented 2 years ago

How was this solved?