search

Conchylicultor / DeepQA

My tensorflow implementation of "A neural conversational model", a Deep learning based chatbot
Apache License 2.0
2.93k stars 1.17k forks source link

Failed to use model-pretrainedv2 #140

Open huqingzhou opened 7 years ago

huqingzhou commented 7 years ago

WARNING: Restoring previous model from /home/centos/DeepQA/save/model-pretrainedv2/model.ckpt Traceback (most recent call last): File "/usr/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1139, in _do_call return fn(*args) File "/usr/lib/python3.6/site-packages/tensorflow/python/client/session.py", line 1121, in _run_fn status, run_metadata) File "/usr/lib64/python3.6/contextlib.py", line 88, in exit next(self.gen) File "/usr/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py", line 466, in raise_exception_on_not_ok_status pywrap_tensorflow.TF_GetCode(status)) tensorflow.python.framework.errors_impl.NotFoundError: Tensor name "embedding_rnn_seq2seq/rnn/embedding_wrapper/multi_rnn_cell/cell_1/basic_lstm_cell/kernel" not found in checkpoint files /home/centos/DeepQA/save/model-pretrainedv2/model.ckpt [[Node: save/RestoreV2_11 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_arg_save/Const_0_0, save/RestoreV2_11/tensor_names, save/RestoreV2_11/shape_and_slices)]]

During handling of the above exception, another exception occurred:

EMCP commented 7 years ago

I'm guessing you are running the correct version of TensorFlow?? , I think it needs to be below 1.2..

I got the same error after running it in v1.2.1 with the script translating the keywords

see https://github.com/Conchylicultor/DeepQA/issues/120#issuecomment-321695344

nichcuta commented 7 years ago

Models updated and trained with tf1.3

adamknaze commented 6 years ago

@nichcuta the link is broken (authorization required)

nichcuta commented 6 years ago

Updated Link Should be working again now.

ondev commented 3 years ago

Updated Link Should be working again now.

Can't download the Models now.