Blacksoil
Blacksoil
Same issue here. Does anybody have ever resolved this issue?
The code has an assumption that the sequences at the same position of each batch are actually subsequent . So all the first sequence of batch 1, 2, 3, ......
Not sure if the you are mentioning the key in raw json files. The raw data uses 'context' rather than 'contextss'.
Same issue here. I think it's because the EntailmentTupleReader is written as the previous version. Have you tried to rewrite this class?
Hi Tushar, Thanks for the reply! I tried to rewrite the code using the latest version and was able to get similar results. I have one more question about adapting...
Hi, thanks for the reply and suggestion :) I did some further analysis and found that indexing operation in theano (eg. indexing of shared variable) took over 90% of the...
I haven't resolved that yet. I'd like to reimplement the code in tensorflow or mxnet and figure out if this is a common issue for these backends.
Hi @eggie5, as I mentioned in this post, I think the indexing operation is the main cause of long execution time. Alternatively, I tried the embedding layer in keras and...
Hi, by indexing I mean using u = T.lvector('u') to get self.U[u]. This indexing corresponds to the 'subIncrease' operation in theano which is time consuming based on my observation. BTW,...