Skip to content

Knowledge Graph Completion with Adaptive Sparse Transfer Matrix

Notifications You must be signed in to change notification settings

FrankWork/transparse

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

18 Commits
 
 
 
 
 
 

Repository files navigation

TranSparse and TensorFlow

Implement the model of TranSparse described in Ji et al., 2016

Training:

# compile c++ op:
$ TF_INC=$(python -c 'import tensorflow as tf; print(tf.sysconfig.get_include())')
$ g++ -std=c++11 -shared norm_prjct_op.cc norm_prjct_kernel.cc -o \
       norm_prjct_op.so -fPIC -I $TF_INC -O2 -D_GLIBCXX_USE_CXX11_ABI=0
$ python3 transparse.py # Train
$ python evaluate.py    # Evaluate

Test and debug:

$ python3 transparse.py --test --debug

About

Knowledge Graph Completion with Adaptive Sparse Transfer Matrix

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published