Giter Club home page Giter Club logo

capsgnn's Introduction

Benedek A. Rozemberczki/ Homepage / Twitter / GitHub / Google Scholar

Welcome stranger

  • โฐ Currently working on machine learning for drug discovery.
  • ๐Ÿค– I would love to collaborate on the machine learning libraries ChemicalX and RexMex.

Great news

capsgnn's People

Contributors

benedekrozemberczki avatar lhbrichard avatar utkarsh87 avatar

Stargazers

avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar

Watchers

avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar

Forkers

francescosaveriozuppichini endruk ml-lab awesome-archive xuehaouwa matic0209 liyaangy fisspoint shadowkun rouniuyizu dlwbm123 hack121 leo-xxx buaaplayer lingguomeng jdc08161063 widemeadows chaoyue729 jonathanchiang caprdzv gnn2qsu aymenwah charlottesean xuewengeophysics juingzhou jacke121 mingli1988 zhujunnan shubhampachori12110095 rjt1990 ximinwu wangdxf desire142 jtpils tj1116 ice-river mingli-ai hookk wuxiujin songfgh alucardmini glshi semchan zhuruijie christinaliang ammieqi changewow messier-16 ye-man bingai geant44 hyzcn trantorrepository avinash-chouhan pandinosaurus tgnco1218 phdshliang emily2he jecktion 1360885769 zlannnn jessicadufirst innat shengyupei qss2012 big-yu shenlant314 liangzhenm hardikgw qinghuazhao zwxxj doublepoints excuses123 frankey419 ariacheng debbiely77 themushrr00m giser18 janaldochen jlqzzz aoe-khkhan batermj sienna13 hujilin1229 codeaudit shashankhalo7 skyewang tcwltcwl jiaxu0017 fengnote wengdunfang courage-chen yukewang96 li-study xmaha plenari nanyuu bowenzzzzzz999 yichengdwu zhh0998

capsgnn's Issues

About dataset

Hi, could you tell me what dataset use in this project?

Reproduce Issues

Hi, thanks for your PyTorch codes of GapsGNN. I try to run the codes on NCI, DD, and other graph classification datasets, but it doesn't work (For example, training loss converges to 2.0, and test acc is about 50% on NCI1 after several iterations.)
How should I do if I want to run these codes on NCI, DD and etc?
Thanks again.

Something about reshape

Hi @benedekrozemberczki ! Thank you for your work!

I have a question at line 61 and 62 of CapsGNN/src/capsgnn.py

hidden_representations = torch.cat(tuple(hidden_representations))
hidden_representations = hidden_representations.view(1, self.args.gcn_layers, self.args.gcn_filters,-1)

Why you directly reshape L*N,D to 1,L,D,N instead of using permutation after reshape, e.g

hidden_representations = hidden_representations.view(1, self.args.gcn_layers, -1,self.args.gcn_filters).permute(0,1,3,2)

Thank you for your help!

Coordinate Addition module & Routing

Hi, thanks for your codes of GapsGNN. And I have some questions about Coordinate Addition module and Routing.

  1. Do you use Coordinate Addition module in this codes?
  2. In /src/layers.py, line 137 : c_ij = torch.nn.functional.softmax(b_ij, dim=0) .
    At this time, b_ij.size(0) == 1, why use dim =0 ?

Thanks again.

Experimental result

Thank you for your work. Then the experimental results I ran out were very different from those in the paper.

Not able to install torch-scatter with torch 0.4.1

Hello,

Thanks for sharing the implementation.

While I'm try to run your code I get some error for installing the environment.
I have torch 0.4.1, but not able to install torch-scatter.Got the following error:
fatal error: torch/extension.h: No such file or directory

But I can successfully install them for torch 1.0.

Is your code working for torch 1.0? Or how to install torch-scatter for torch 0.4.1?

Details:

$ pip list
Package Version

backcall 0.1.0
certifi 2018.8.24
....
torch 0.4.1.post2
torch-geometric 1.1.1
torchfile 0.1.0
torchvision 0.2.1
tornado 5.1
tqdm 4.31.1
traitlets 4.3.2
urllib3 1.23
visdom 0.1.8.5
vispy 0.5.3
.... ....

$pip install torch-scatter

how to repeat your expriments?

Enumerating feature and target values.

100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 60/60 [00:00<00:00, 14754.82it/s]

Training started.

Epochs: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 10/10 [00:05<00:00, 1.90it/s]
CapsGNN (Loss=0.7279): 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 1/1 [00:00<00:00, 1.92it/s]

Scoring.

100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 30/30 [00:00<00:00, 128.47it/s]

Accuracy: 0.3333

Accuracy is too small

How to generate such dataset

When I transfer the MUTAG to the specific json file, the accuracy is only round 62%. Can you give me some suggestion or the generate file

Other datasets

I notice some datasets in your paper such as RE-M5K and RE-M12K. May I know how to obtain these datasets? The processed datasets would be appreciated. Thank you.

่ฟ่กŒไปฃ็ ๅฐฑๆŠฅ้”™๏ผŸ้ƒฝๆฒกไฟฎๆ”น

Traceback (most recent call last):
File "src/main.py", line 19, in
main()
File "src/main.py", line 14, in main
model.fit()
File "/lmq/CapsGNN/src/capsgnn.py", line 293, in fit
prediction, reconstruction_loss = self.model(data)
File "/usr/local/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "/lmq/CapsGNN/src/capsgnn.py", line 147, in forward
first_capsule_output = self.first_capsule(hidden_representations)
File "/usr/local/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "/lmq/CapsGNN/src/layers.py", line 86, in forward
u = [self.unitsi for i in range(self.num_units)]
File "/lmq/CapsGNN/src/layers.py", line 86, in
u = [self.unitsi for i in range(self.num_units)]
File "/usr/local/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl
return forward_call(*input, **kwargs)
File "/usr/local/miniconda3/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 313, in forward
return self._conv_forward(input, self.weight, self.bias)
File "/usr/local/miniconda3/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 309, in _conv_forward
return F.conv1d(input, weight, bias, self.stride,
RuntimeError: Expected 2D (unbatched) or 3D (batched) input to conv1d, but got input of size: [1, 2, 20, 15]

D&D dataset

I notice some datasets in your paper such as D&D dataset. May I know how to obtain these datasets? The processed datasets would be appreciated. Thank you.

Train on Image Dataset

Hi.. thanks for sharing this repo.
What in need to modify so I can train this on an image dataset?
Thanks

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.