Konquer your Mind

for nv hand gesture dataset, every video clip contain one continuous occurring gesture definitely. so the label sequence contains only one class label (>=0). there is no label for no...

ctc outputs a vector rather than a scalar. you cant use accuracy with its output.发自我的华为手机-------- 原始邮件 --------主题：[breadbread1984/R3DCNN] evaluation accuracy (#6)发件人：sunnymoon155 收件人：breadbread1984/R3DCNN 抄送：Subscribed hi, the eval result is mean_edit_distance, could I...

please use the eager training script

I am sorry, I can't access google from my network.

the model is nearly 700MB. it is too large to fit in an email attachment.