Louis

seq2seq模型运行时错误：ValueError: too many values to unpack (expected 2)

1

首先感谢楼主的分享，对于basic_seq2seq中的代码，运行时产生如下错误，我的tensorflow是最新的1.3.0 gpu版本，执行时所有代码均未改动，想楼主帮看看 Traceback (most recent call last): File "D:\Workspaces\Eclipse\PythonLearn1\src\seq2seq\__init__.py", line 227, in num_layers) File "D:\Workspaces\Eclipse\PythonLearn1\src\seq2seq\__init__.py", line 189, in seq2seq_model decoder_input) File "D:\Workspaces\Eclipse\PythonLearn1\src\seq2seq\__init__.py", line 146, in decoding_layer maximum_iterations=max_target_sequence_length) ValueError: too many...

what is 'input_aspect'

1

Hi Can I ask that what is input_aspect ? Is the aspect like query terms? If so , then what is training[1] in 'history = nn_model.fit(training[0], training[1]' of model_target.py ?

Hello, in the folder of "models", you wrote "Here you find folders. Each folder represents a model (full of data, CRF models, headers and topology graphs).", but there is no...

How to reproduce the behaviour --------- Your Environment --------- * Operating System: * Python Version Used: * When you install doccano: * How did you install doccano (Heroku button etc):