search

clovaai / deep-text-recognition-benchmark

Text recognition (optical character recognition) with deep learning methods, ICCV 2019
Apache License 2.0
3.75k stars 1.1k forks source link

use --sensitive ,characters have been changed #372

Open Carolyn0822 opened 1 year ago

Carolyn0822 commented 1 year ago

character: 动力电池总成系统种类物料编码压额定容量重产品号ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstvuwxyzAhkgKV-0123456789 sensitive: False PAD: False data_filtering_off: True Transformation: TPS FeatureExtraction: ResNet SequenceModeling: BiLSTM Prediction: Attn

============================================================== character: 0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ!"#$%&'()*+,-./:;<=>?@[]^_`{|}~ sensitive: True PAD: False data_filtering_off: True Transformation: TPS FeatureExtraction: ResNet SequenceModeling: BiLSTM Prediction: Attn

I add the --sensitive into the config,the characters have been changed. What should I do if I want the model to recognize chinese , letter(sensitive) and numbers?

creati0nix commented 1 year ago

add you char list into the train.py and dont use --sensitive. https://github.com/clovaai/deep-text-recognition-benchmark/issues/85 read this.