A-bone1/Attention-ocr-Chinese-Version

How to make tfRecord file for using this 'train.py'

Opened this issue · 1 comments

plz tell me....

p.s : my datasets have about 7-8 length so, I write to 'my_fsns.py' "max_sequence_length" = 8,
In conclusion, my data predict 7 length sentence -> 8 length sentence In "demo_inference.py"
How to solve this problem....?
I think this problem is derived from how to make tfRecord.