Open tomhosking opened 2 years ago
I am trying to reappear this error and will reply to you soon.
Hi, 这个溢出是因为gumble_softmax的并没有按照论文里说的那样设置。在文件run.py 里面 ‘self.GS = gumble_softmax(3500, 100)‘,即N=3500、Tau_max=100
,仔细查看代码会发现,每一步,n+=1
,随着训练步数增加,n越来越大,self.tau_max ** (self.n / self.N)
将会出现溢出错误。
Hi, this overflow is because gumble_softmax did not set as mentioned in the paper. In the file run.py
, ‘self.GS = gumble_softmax(3500, 100)‘, that is, n = 3500, tau_max = 100
, check the code carefully, you will find that every step,n+= 1
, with the number of training steps increase, n is getting bigger and bigger, self.tau_max ** (self.n / seld.n)
will have an overflow error.
Hi,
During training, I get the following error:
This happens after a few days of training, around epoch 39 for MSCOCO and epoch 77 for Quora.
The command used was: