practical_seq2seq

practical_seq2seq copied to clipboard

Importing using the last check point

3

Attempting to use uninitialized value decoder/embedding_rnn_seq2seq/embedding_rnn_decoder/embedding/Adam_1 [[Node: decoder/embedding_rnn_seq2seq/embedding_rnn_decoder/embedding/Adam_1/read = Identity[T=DT_FLOAT, _class=["loc:@decoder/embedding_rnn_seq2seq/embedding_rnn_decoder/embedding"], _device="/job:localhost/replica:0/task:0/cpu:0"](decoder/embedding_rnn_seq2seq/embedding_rnn_decoder/embedding/Adam_1)]]

charan16

TypeError: cannot create 'sys.version_info' instances

2

i am getting TypeError: cannot create 'sys.version_info' instances on executing the "python 03-Twitter-chatbot.py". File "C:\Users\tmpuser4195\AppData\Local\Programs\Python\Python35\Lib\copy.py", line 243, in _deepcopy_dict y[deepcopy(key, memo)] = deepcopy(value, memo) File "C:\Users\tmpuser4195\AppData\Local\Programs\Python\Python35\Lib\copy.py", line 182, in deepcopy...

SamirMatkar

Hi,folks I've tried several hyperparameters for the cornell-dialogue-corpus,but I didn't get a good result. What hyperparameters have you guys tried?

PedroPei

Update seq2seq_wrapper.py

1

Answer to this issue :https://github.com/suriyadeepan/practical_seq2seq/issues/47 I think it is due to the tensorflow upgraded libraries

mandar1010

Hi , I Want to make a chat bot in different languages? How can I do that using tensorflow ? Thanks

phpmind

In cases where there is no explicit need for 2 vocabs (unlike NMT), should we have 2 separate vocabularies or just use one?

LeenaShekhar

When i try to train using my own data using only cpu(not gpu),I get killed error by os.Is it because we can perform training only using gpu for this project?

rojansudev

OOM when allocating tensor with shape[2048,4096]

1

When i try to run `python 04-Cornell-Movie-Dialog-Bot.py` get this error: ``` I c:\tf_jenkins\home\workspace\release-win\device\gpu\os\windows\tensorflow\core\common_runtime\bfc_allocator.cc:678] Chunk at 000000079CFE2100 of size 33554432 I c:\tf_jenkins\home\workspace\release-win\device\gpu\os\windows\tensorflow\core\common_runtime\bfc_allocator.cc:678] Chunk at 000000079EFE2100 of size 33554432 I c:\tf_jenkins\home\workspace\release-win\device\gpu\os\windows\tensorflow\core\common_runtime\bfc_allocator.cc:678] Chunk...

felansu

Hi @suriyadeepan I'm running the prepare_data.py and it outputs the following message, but doesn't create any encoder or decoder files - any help much appreciated! Grahams-MacBook-Air:scripts grahamrksmith$ python prepare_data.py >>...

GrahamRKSmith

I guide on adding beam search in this example would be beneficial.

PratsBhatt