Cong Feng

Sorry for late reply but I am glad my issue gains concern finally. Well, I have tried a workaround. Although it is stupid, I'd like to share: ```vim "" "...

No really. I am currently busy on school homework project and forgot this issue long ago. I do vimscript mainly for self interest. By the time I post this issue,...

I saw the same problem. Could you share your run configure with me? If that was still there.

Well, I managed to fix it last night. I use the code in atten/model.lua to fill in the hole. I am still work on it.

I rename the file `data.lua` to `Dataset.lua`.

I got the same error, but the training script didn't stop for that. Command I used: ssh://[email protected]:22:docker run --runtime nvidia -v /home/cgsdfc/deployment/HRED-VHRED:/root/HRED-VHRED -v /home/cgsdfc/UbuntuDialogueCorpus:/home/cgsdfc/UbuntuDialogueCorpus -w /root/HRED-VHRED -e PYTHONPATH=/root/HRED-VHRED ufoym/deepo:theano-py36-cu90 python...

I hit the same problem, here is the log: ``` Traceback (most recent call last): File "/usr/local/lib/python3.6/dist-packages/theano/compile/function_module.py", line 903, in __call__ self.fn() if output_subset is None else\ File "pygpu/gpuarray.pyx", line...

I think I've found a simple fix ```python self.max_len = len(context) + 1 ``` See [the full context](https://github.com/cgsdfc/HRED-VHRED/blob/5e5bb76337d084aef598af75de3f893eb8fd5484/serban/search.py#L101). The idea is setting `self.max_len` to the length of the context being...

I am sorry to announce that the fix proposed in my previous comment will *cause the training of VHRED* to break. Thus it is not a fix at all. The...

Will someone post a fix to this? I will be much much appreciative!