eschnou
eschnou
Unfortunately, it seems distributed seq2seq is not straightforward. The only approach seems to be splitting the LSTM hidden layers accross GPUs but doing so can result in one GPU having...
Here is another interesting link on the subject, comparing data paralelism and model paralelism for seq2seq. It seems the model paralelism is really the way to go but challenging to...
Wrong copy paste. Link is updated.
Actually, there is a scope argument to the method embedding_rnn_seq2seq, so this might be what you need to use to scope your two models properly. See here in the TF...
@Conchylicultor I don't think this will work in our case. By sampling the output soft-max you only sample the last output, so you will get a list of candidates for...
Ha ok, I was still focusing on generating n-best candidate solutions. With your approach, you effectively introduce variation but still only generate one output. Already a good start indeed to...
+1 on the quote style idea. It shouldn't be too hard, based on the current post/link implementation. I would be happy to review a pull-request on this!
No idea. Can you provide us with the version of your MySQL server and other details of your setup ? Thanks !
Weird, because I generated the file using mysql itself. The problem is in the core schema that the installer tries to load: protected/install/database/schema/core.sql You can try to fix this file...
Might be a duplicate friom issue #18 by the way. Still no clue what is going on here.