michaelfarrell76 / end-to-end-generative-dialogue Goto Github PK
View Code? Open in Web Editor NEWA neural conversation model
A neural conversation model
rzai@rzai00:~/prj/End-To-End-Generative-Dialogue/src$ CUDA_VISIBLE_DEVICES=0 th train.lua -data_file data/conv-train.hdf5 -val_data_file data/conv-val.hdf5 -save_file conv-model -gpuid 1
nil
Using CUDA on GPU 1...
Loading data...
Source vocab size: 10005, Target vocab size: 10005
Source max sent len: 7, Target max sent len: 7
Done loading data!
Building model with specs:
Layer type: lstm
Model type: red
Embedding size: 300
Hidden layer size: 300
Number of layers: 2
Using pre-trained word embeddings from data/word_vecs.hdf5
Number of parameters: 11902905
Beginning training...
Using ada_grad
/home/rzai/torch/install/bin/luajit: ...i/torch/install/share/lua/5.1/rnn/SequencerCriterion.lua:47: expecting target table
stack traceback:
[C]: in function 'assert'
...i/torch/install/share/lua/5.1/rnn/SequencerCriterion.lua:47: in function 'forward'
model_functions.lua:359: in function 'train_ind'
model_functions.lua:547: in function 'train_batch'
model_functions.lua:638: in function 'train'
train.lua:184: in main chunk
[C]: in function 'dofile'
...rzai/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:145: in main chunk
[C]: at 0x00406670
rzai@rzai00:~/prj/End-To-End-Generative-Dialogue/src$
Hi.
I'm parsing through your code and I'm trying to figure out where you are using MMI (maximum mutual information) criterion. Could you please point that out? Thanks
can you please give me the MovieTriples dataset, I am doing it for a personal research project.
my email is: [email protected]
Thanks
rzai@rzai00:/prj/End-To-End-Generative-Dialogue/src$ python preprocess.py/prj/End-To-End-Generative-Dialogue/src$
Traceback (most recent call last):
File "preprocess.py", line 656, in
sys.exit(main(sys.argv[1:]))
File "preprocess.py", line 652, in main
format_data(args)
File "preprocess.py", line 396, in format_data
data_dict = load_data()
File "preprocess.py", line 352, in load_data
with open('%s%s/%s' % (args.input_directory, data_set, data_file)) as f:
IOError: [Errno 2] No such file or directory: '../data/MovieTriples/Training.dict.pkl'
rzai@rzai00:
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ 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. ๐๐๐
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 โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.