Failed to load the native TensorFlow runtime. about nmt-chatbot HOT 6 CLOSED

Ok, so this is actually a bug with TensorFlow it seems.

The problem seems to be that tensorflow-gpu is version 1.6 when we need 1.4. So the following command fixed it for me (of course after hours of scratching my head I figure it out right after posting :))

pip install --upgrade tensorflow-gpu==1.4

I found the solution here: tensorflow/tensorflow#15604

from nmt-chatbot.

Interesting, i have to checkt that.
I am using TF 1.5 (on Windows machine) successfully with that code.

from nmt-chatbot.

/home/tensorflow/Desktop/lib/python3.6/importlib/_bootstrap.py:219: RuntimeWarning: compiletime version 3.5 of module 'tensorflow.python.framework.fast_tensor_util' does not match runtime version 3.6
return f(*args, **kwds)

Training model...

Epoch: 1, learning rate: 0.001 - already passed
Epoch: 2, learning rate: 0.0001 - already passed
Epoch: 3, learning rate: 1e-05 - already passed

Training finished

Do i need to again go back to 3.5 because it already gives exceptions?

from nmt-chatbot.

Try pip install tensorflow --upgrade --force-reinstall
use tensorflow-gpu for gpu version of course.

from nmt-chatbot.

$ python train.py
Output
Training model...
Epoch: 1, learning rate: 0.001 - already passed
Epoch: 2, learning rate: 0.0001 - already passed
Epoch: 3, learning rate: 1e-05 - already passed

Training finished
$ python .\inference.py

Starting

interactive mode (first response will take a while):

hey
Traceback (most recent call last):
File ".\inference.py", line 308, in
answers = inference_internal(question)[0]
File ".\inference.py", line 212, in inference_internal
return process_questions(questions, True)
File ".\inference.py", line 260, in process_questions
answers_list = inference_helper(prepared_questions)
File ".\inference.py", line 181, in start_inference
return inference_helper(question)
File ".\inference.py", line 174, in
inference_helper = lambda question: do_inference(question, *inference_object)
File ".\inference.py", line 98, in do_inference
loaded_infer_model = nmt.inference.model_helper.load_model(infer_model.model, flags.ckpt, sess, "infer")
File "C:\Python\ChatBot\nmt-chatbot/nmt\nmt\model_helper.py", line 483, in load_model
model.saver.restore(session, ckpt)
File "C:\Users\Test\AppData\Local\Programs\Python\Python36\lib\site-packages\tensorflow\python\training\saver.py", line 1662, in restore
raise ValueError("Can't load save_path when it is None.")
ValueError: Can't load save_path when it isNone.

I am getting above error on windows 10.@daniel-kukiela Could you please help me on this ?
Note : No Checkpoint files created in Model directory.

from nmt-chatbot.

@TestPW for some, unknown for me, reason, there is training progress saved in model subfolder. Remove epochs_passed file, and try again,

from nmt-chatbot.