domerin0 / neural-chatbot Goto Github PK
View Code? Open in Web Editor NEWA chatbot based on seq2seq architecture done with tensorflow.
A chatbot based on seq2seq architecture done with tensorflow.
HI inikdom,
My stack is-
python -3.6
tensorflow -1.2
pycharm IDE- 2017
I am getting following error while running sample.py file (specified checkpoint dir and data dir) ---
Traceback (most recent call last):
File "sample.py", line 101, in
main()
File "sample.py", line 32, in main
model = load_model(sess, FLAGS.checkpoint_dir)
File "sample.py", line 78, in load_model
model = models.chatbot.ChatbotModel(vocab_size=FLAGS.vocab_size,
File "/home/sysadmin/anaconda3/bin/3.6/bin/3.6/lib/python3.6/site-packages/tensorflow/python/platform/flags.py", line 50, in getattr
raise AttributeError(name)
AttributeError: vocab_size
Please resolve this issue at the earliest.
Thanks in advance
Hello,
I would like to know the pattern in which I need to provide the dataset to the program. If possible please add some test datasets, so that the idea will be clear.
Hi there,
I implemented your code in Tensroflow r1.1 and I am able to train the entire model.
When I then attempt to get a sample, I simply get a constant output [ 2, 2, 2, 2, 2 ]
This means that the trained model outputs _EOS every time.
Any ideas as to why this is happening?
Hello chatbot, how are you?
Traceback (most recent call last):
File "sample.py", line 125, in
main()
File "sample.py", line 68, in main
bucket_id = min([b for b in xrange(len(_buckets))
ValueError: min() arg is an empty sequence
Traceback (most recent call last):
File "sample.py", line 101, in
main()
File "sample.py", line 32, in main
model = load_model(sess, FLAGS.checkpoint_dir)
File "sample.py", line 79, in load_model
hidden_size=FLAGS.hidden_size,
File "/Users/LymanYoung/anaconda3/lib/python3.5/site-packages/tensorflow/python/platform/flags.py", line 50, in getattr
raise AttributeError(name)
AttributeError: hidden_size
Hi, is it language independent? I could fill in by mixing dialog of Spanish and Japanese in the corpus? Thanks!
Traceback (most recent call last):
File "train.py", line 18, in
import models.chatbot
File "/home/vinicius_torrecillas/neural-chatbot/models/chatbot.py", line 13, in
from tensorflow.python.ops import rnn, rnn_cell, seq2seq
ImportError: cannot import name rnn_cell
how can i fix this?
When I run python sample.py
it just hangs. What should I expect? How long should I be waiting?
My understanding of sample.py is that it's the tester..so why is it training again?
python sample.py --checkpoint_dir="data/checkpoints/" --data_dir="data"
File "sample.py", line 88
decoder_mode=False, True)
SyntaxError: non-keyword arg after keyword arg
I am using tensorflow 1.3
how can I create a corpus like cornell movie`s corpus?
I have a bunch of questions&answers in MySQL format and I want use them n this code
I use this do :$ python util/sequencelengthplotter.py --data_dir="path/to/raw_data_files"
Traceback (most recent call last):
File "util/sequencelengthplotter.py", line 98, in
main()
File "util/sequencelengthplotter.py", line 67, in main
plotHistoLengths("target lengths", target_lengths)
File "util/sequencelengthplotter.py", line 93, in plotHistoLengths
plt.xlim(0,max(lengths))
ValueError: max() arg is an empty sequence
how "data_source_test.txt" & "data_target_test.txt" file's data format may i need.
Has any data template ?
hello, I want to ask questions about the cornell lines, is it from cornell movies dialogs? https://www.cs.cornell.edu/~cristian/Cornell_Movie-Dialogs_Corpus.html
And how you get it?
Hello,
When I run train.py
(python train.py
) I have this error :
Traceback (most recent call last):
File "/home/judemont/autre/neural-chatbot/train.py", line 17, in <module>
import models.chatbot as chatbot
File "/home/judemont/autre/neural-chatbot/models/chatbot.py", line 15, in <module>
from tensorflow.contrib import rnn, seq2seq
ModuleNotFoundError: No module named 'tensorflow.contrib'
Python Version : 3.11.2
tensorflow==2.12.0
OS : ubuntu 23.04
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.