Comments (6)
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.
Related Issues (20)
- Chatbot only produces 1 answer despite beam width being 20 HOT 4
- Can't run train.py HOT 7
- Train.py says it's finished training after 1 second. HOT 2
- ERROR: cannot import name 'nmt' from 'nmt' HOT 2
- FileNotFoundError: [Errno 2] No such file or directory: 'data//corpus_size'
- nmt: [ deleted ] while training
- Trained Model ? HOT 1
- does this work with tensorflow 2.0?
- is it supposed to just be stopped on this
- 2021-05-06 22:03:17.947802: I tensorflow/core/kernels/shuffle_dataset_op.cc:121] Shuffle buffer filled.
- decoding to output F:\Nebula0.0.5\nmt-chatbot\model\output_dev.
- from nmt import nmt : error
- TypeError: 'encoding' is an invalid keyword argument for this function HOT 1
- Inference returning the same empty answer to everything i type HOT 1
- bot producing only one translation per input
- Cannot Downgrade Tensorflow 1.x on Google Colab
- how do i make it train more epoch like 10000
- cannot import name 'nmt' from 'nmt'
- Issue with tensorflow api and pip installation candidate missing before 2.x
- cannot import name 'lookup_ops' from 'tensorflow.python.ops'
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from nmt-chatbot.