Yuntian Deng
Yuntian Deng
btw, did you install lua-torch on colab youself? I don't think colab comes with lua-torch, but maybe I'm wrong.
Hmm weird, can you directly try ``` require 'opennmt.init' ``` in `th`?
such as `th -e 'require opennmt.init'` and see what's the error msg.
Hmm it might be due to the opennmt installed in rocks, can you remove `/root/.luarocks/lib/luarocks/rocks/opennmt`? Like by ``` !rm -rf /root/.luarocks/lib/luarocks/rocks/opennmt ```
Thanks for your interest! Currently we are using cudnn in the CNN part, so we cannot run on pure CPU environment. However, I think you can use `cudnn.convert` (https://github.com/soumith/cudnn.torch#conversion-between-cudnn-and-nn) to...
Sure I'll check.
Sorry that Im2Text doesn't support multi-gpu for now.
Thanks for your interest in our work, my email is [email protected]. One thing to note is that we only work on public datasets (or datasets that can be released later),...
Regarding hardware, I think it's almost impossible to train on CPU, it would probably take forever. For GPU training would take less than a day even using 100k images. On...
btw, if you got a GPU instance, I would recommend using this dockerfile to save you the trouble of installing luaTorch: https://github.com/OpenNMT/OpenNMT/blob/master/Dockerfile