Is there an error inside the _eval_epoch function?

[Tesla-jiang]

Is there an error inside the _eval_epoch function?

After debugging, I found that this function would enter an endless loop, and no operation could overflow it, and [batch] acquisition of batch data seems to never be exhausted. Is there any mistake in my operation?

Looking forward to your reply!

[Simons2017]

Is there an error inside the _eval_epoch function?

After debugging, I found that this function would enter an endless loop, and no operation could overflow it, and [batch] acquisition of batch data seems to never be exhausted. Is there any mistake in my operation?

Looking forward to your reply!

Hello, I met the same problem. How did you solve it?@1172135979

[andrewmoses]

Is there an error inside the _eval_epoch function?

After debugging, I found that this function would enter an endless loop, and no operation could overflow it, and [batch] acquisition of batch data seems to never be exhausted. Is there any mistake in my operation?

Looking forward to your reply!

Even I'm facing the same problem. If there is any work around pls share

[ghost]

Hi, Just want to check if someone facing this problem has found a workaround? I'm also facing the same issue. Please share the workaround.

[nehac4371]

Facing the same problem.

[Victor0118]

Fixed by setting is_training to False here: https://github.com/santhoshkolloju/Abstractive-Summarization-With-Transfer-Learning/blob/master/model.py#L32

[ghost]

Hi @Victor0118 Thanks for the response. The fix you suggested seems to be working however, I've got into another error here

Abstractive-Summarization-With-Transfer-Learning/texar_repo/examples/transformer/bleu_tool.py

Line 134 in 745b026

ratio = translation_length / reference_length

. In console it says ZeroDivisionError: division by zero. Would you be able to tell what went wrong and how to fix this?