tf-seq2seq
tf-seq2seq copied to clipboard
jayparks
Sequence to sequence learning using TensorFlow.
Thank you very much for your contribution. I am not familiar with NMT. Could you provide me the address for downloading the sample.src and sample.trg?
Hi, I got the file missing error. Was it deleted? No such file or directory: 'data/europarl-v7.1.4M.de' Thanks.
preprocessing created a bunch of files. which of these files are data params and which data params are required?? --source_vocabulary : Path to source vocabulary --target_vocabulary : Path to target...
In the documentation, it is suggested to make **attn_input_feeding** =**True** during decoding. But in the code, I don't see any place where it is set to True during decoding. The...
am getting issue related to miss match of state and output. But I am unable to figure the issue. It would be really appreciated if someone can guide me. Thanks...
I'm trying to use pre-embedded data as input. It means I don't want to use embedding layer of model. How should I do this? Need for help.
Can you clarify a bit on how you are taking the validation data and why bpe is used in such cases ? tf.app.flags.DEFINE_string('source_valid_data', 'data/newstest2012.bpe.de', 'Path to source validation data') tf.app.flags.DEFINE_string('target_valid_data',...
In seq2seq_model.py file, I use bi-directional GRU for encoder but I got an error. More specifically,in line 391, i got an error as follows "TypeError: Tensor objects are not iterable...
when i test this code with the dataset of europarl-v7.1.4M.en , the decoder result is not true, most line is .i am confused. I have solved.
