zhangying

hello, the code you use to read the ground truth of dataset is ``` gt_temp = cv2.imread(os.path.join(gt_path,piece+'.png'))[:,:,0] gt_temp[gt_temp == 255] = 0 ``` why there is "[:,:,0]" for the ground...

the learning rate of word_language_model

3

Hi, I have a question about the learning rate in the example "word_language_model", the init lr = 20, which seems very large, can you tell me why lr is set...

条件熵公式如下，应是联合概率，文中写成了条件概率。

请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem - 系统环境/System Environment：ubuntu 18.04 - 版本号/Version：Paddle：2.3 PaddleOCR：2.6 问题相关组件/Related components：deploy - 运行指令/Command Code：deploy/lite/ocr_db_crnn.cc - 完整报错/Complete Error Message： 由于想使用paddle lite同时兼顾x86和Android的部署，先尝试了paddle lite x86的部署，...

Thank you for your valuable work! In the data.py, I find the preprocess for the dataset SVHN, MNIST and DomainNet dataset ["real", "quickdraw", "sketch", "infograph", "painting", "clipart"]. No code is...