xiaomaxiao comments

Results 15 comments of


                                            xiaomaxiao

exuse me！！！！i have question,my data is image which full of long words,just like books,but when i train model by my data,it can not detect all the words in one line.maybe it can only detect half of a line and my input_size is 768 and text_scale is 768.could you tell me where i maybe wrong?thank you so much

@cjt222 I also face such a problem, do you have a solution?

exuse me！！！！i have question,my data is image which full of long words,just like books,but when i train model by my data,it can not detect all the words in one line.maybe it can only detect half of a line and my input_size is 768 and text_scale is 768.could you tell me where i maybe wrong?thank you so much

@ravikantb now , i use ctpn

exuse me！！！！i have question,my data is image which full of long words,just like books,but when i train model by my data,it can not detect all the words in one line.maybe it can only detect half of a line and my input_size is 768 and text_scale is 768.could you tell me where i maybe wrong?thank you so much

@ravikantb yes , we can talk together 。

Training on numbers dataset !

@darraghdog I found the real image padding the same size although has different num of characters . so I should make same number of characters in batch ?

四层特征图进行融合得到特征图用F表示

是

What are those output shapes of lambda_1 & blstm layers in ctpn?

eg. rpn_conv1 is [batchsize=1,32,32,512] lambda_1 (Lambda) = (1*32,32,512) Bidirectional(LSTM(128,return_sequences=True), =128 +128 = 256 =>(1*32,32,256) lambda_2 (Lambda) = (1,32,32,256)

About pre-processing of Image datasets

the best way to understand ctpn and crnn is to read the original paper .

对英文句子识别好像不太好

把空格当作单独的一个类别加入训练就可以了，这个模型主要做的汉字，英语料少也没有加入空格训练

为什么把中英文实验分开做呢？

@senlinuc 试验过英文CNN+LSTM+CTC 没有出现丢字符的情况。是不是英文太少，或者语料中中英应该在一起、？

关于default.yaml文件配置问题

@xdwjc 我也遇到同样问题，我限制了角度，稍微好了一些 #21