valdersoul / graphbtm Goto Github PK
View Code? Open in Web Editor NEWCode for paper "GraphBTM: Graph Enhanced Autoencoded Variational Inference for Biterm Topic Model". Under preparation.
Code for paper "GraphBTM: Graph Enhanced Autoencoded Variational Inference for Biterm Topic Model". Under preparation.
Hi, thank you for sharing the code. I was wondering how can we infer topic document distribution probability from the word topic distribution probability generated by Graph-BTM?
the sample dataset 20news takes a small vocabulary size of 1995, therefore, the adj becomes a 1995*1995 tensor. But if I make a larger vocabulary size, the adj matrix will be very big I couldn't be sure whether it will work.
I couldn't find instruction to generate the following files for a new corpus.
test.txt.npy, train.txt.npy, valid.txt.npy, vocab.pkl
Regarding the new corpus, would it be sufficient if I supply the text its text in data/20news_clean/corpus.txt
?
Hi, I tried to run your code without GPU and it asked for GPU.
Any suggestion? Thanks.
python pytorch_run.py --start --nogpu
loading biterms
Data Loaded
11258
start training
Traceback (most recent call last):
File "pytorch_run.py", line 243, in <module>
train(dataset)
File "pytorch_run.py", line 157, in train
biterm = torch.FloatTensor(biterm).float().cuda()
File "/local/tcao/topic_modeling/GraphBTM/.env/lib/python3.6/site-packages/torch/cuda/__init__.py", line 161, in _lazy_init
_check_driver()
File "/local/tcao/topic_modeling/GraphBTM/.env/lib/python3.6/site-packages/torch/cuda/__init__.py", line 82, in _check_driver
http://www.nvidia.com/Download/index.aspx""")
AssertionError:
Found no NVIDIA driver on your system. Please check that you
have an NVIDIA GPU and installed a driver from
http://www.nvidia.com/Download/index.aspx
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.