Comments (5)
Hello,
Same here with python 2.7. Is there any workaround ?
from gem.
I fixed it by manually setting the dictionary of parameters, yet the problem given in example seems to remain.
from gem.
Hi,
Sorry for the delay in reply. I have modified the readme code to address the changes in the code. Now you need to specify the name of each input argument i.e. GraphFactorization(2, 100000, 110**-4, 1.0) has changed to GraphFactorization(d=2, max_iter=100000, eta=110**-4, regu=1.0)
from gem.
Ok, thanks @palash1992 . I have this error now:
ValueError Traceback (most recent call last)
in ()
41 print (embedding._method_name+':\n\tTraining time: %f' % (time() - t1))
42 # Evaluate on graph reconstruction
---> 43 MAP, prec_curv = gr.evaluateStaticGraphReconstruction(G, embedding, Y, None)
44 # Visualize
45 viz.plot_embedding2D(embedding.get_embedding(), di_graph=G, node_colors=None)
ValueError: too many values to unpack
from gem.
It has been fixed. The evaluation function now also returns error of reconstruction and baseline error. Thus, MAP, prec_curv = gr.evaluateStaticGraphReconstruction(G, embedding, Y, None) should now be MAP, prec_curv, err, err_baseline = gr.evaluateStaticGraphReconstruction(G, embedding, Y, None)
from gem.
Related Issues (20)
- Error in SDNE
- Tensorflow module is missing
- sdne: Nodes corresponding to embedded vectors HOT 1
- Problem with dependencies HOT 3
- LaplacianEigenmap for a large number of connected components HOT 3
- result of the running example of readme.md HOT 2
- The use of "merge" module of keras.layers in sdne.py HOT 2
- EXECUTION HOT 3
- SDNE execution problem HOT 1
- how to use GEM in an exsisting graph HOT 4
- gf not found HOT 2
- Use of Link prediction code HOT 2
- The number of positive classes for each node is leaked to TopKRanker HOT 1
- How to determine dimension variable in methods HOT 1
- Create embeddings directly from an adjacency matrix (e.g. numpy.array or scipy.sparse)? HOT 2
- [Errno 2] No such file or directory: 'gem/intermediate/karate_gf.graph' HOT 7
- SDNE implementation error HOT 3
- Error when running link prediction
- Unweighted node2vec not possible?
- Error running SDNE algorithm HOT 1
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 gem.