zhhhzhang

Could u please leave the original code for us to follow??wanna see some details on it

太棒啦！多谢大佬 期待更新 ---原始邮件--- 发件人: "HT Liu"

> Can you tell me what does -1 means in wgt_ne and wgt_rel? Hi, could you share the pre-preprocessing code and data? THx

> Hi, thanks for interested in my work. > > Sorry for missing the pre-preprocessing code and data. (I left my previous lab and forgot to backup) > I will...

Thanks for you reply! My email is [email protected] ------------------ 原始邮件 ------------------ 发件人: "LuoXukun"

没有呢，还没要到数据[捂脸] 你有数据么？ 发一份呗 ------------------ 原始邮件 ------------------ 发件人: "zhengnt"

> I tried to use : > config = tf.ConfigProto() > config.gpu_options.per_process_gpu_memory_fraction = 0.9 > config.gpu_options.allow_growth=True > config.log_device_placement=True > > Althought the Gpu memory use less, but when runing eval,...

> excuse me，after i run your code in my dataset，i found the va_loss is going up ，but train loss is going down.so > So，Have you ever encountered this situation when...

> 照read 请问您安装成功了么？ 我这边一直装不上...不知道为啥

+1