Comments (3)
Hi @c747903646,
We didn't conduct unsupervised_TU on GITHUB dataset (but do in semisupervised_TU). It looks like the edge index get mismatches when x = F.relu(self.convs[i](x, edge_index))
is executed. Would you confirm that via (i) trying other datasets e.g. NCI1 with the same script, and (ii) running on GITHUB dataset semisupervised setting?
from graphcl.
Hi @c747903646,
We didn't conduct unsupervised_TU on GITHUB dataset (but do in semisupervised_TU). It looks like the edge index get mismatches when
x = F.relu(self.convs[i](x, edge_index))
is executed. Would you confirm that via (i) trying other datasets e.g. NCI1 with the same script, and (ii) running on GITHUB dataset semisupervised setting?
Yes, I have run the same script on other TU datasets, such as COLLAB, DD, NCI1, RDT-5K and RDT-B, and all work except run on GITHUB. Meanwhile, semisupervised codes work all TU datasets, including GITHUB.
In debugging, I found that before x = F.relu(self.convs[i](x, edge_index))
is excuted, the dimension of x
is matched with self.convs[i]
. So I could not understand the error info, srcIndex < srcSelectDimSize
.
from graphcl.
Mismatch could happen if edge_index.max()+1 > x.shape[0]
, which is my suspect.
from graphcl.
Related Issues (20)
- Question about the loss function in the transferLearning_MoleculeNet_PPI/chem HOT 1
- About Unsupervised_Cora_Citeseer HOT 1
- Different result about Transfer Learning HOT 2
- ValueError: `MessagePassing.propagate` only supports `torch.LongTensor` of shape `[2, num_messages]` or `torch_sparse.SparseTensor` for argument `edge_index`. HOT 1
- Question about GraphCL HOT 1
- Question About Sungraph HOT 1
- Question about data augmentation HOT 1
- Question about Unsupervised_TU HOT 4
- Unsupervised learning with self created dataset HOT 1
- graph classification HOT 1
- 问题请教 HOT 1
- A question about Semisupervised_TU in pre_training HOT 1
- 运行过程未结束就‘Early stopping!’ HOT 1
- Question about Unsupervised_TU experiments details HOT 4
- Question about Unsupervised-TU ''test'' and ''val'' HOT 1
- How to use for Graph Clustering. HOT 1
- information about the datasets HOT 1
- Question about cortex_DIM in net_infomax.py of semisupervised_TU/finetuning HOT 2
- File "/home/test02/code/GraphCL-master/semisupervised_TU/pre-training/feature_expansion.py", line 27, in __init__ super(FeatureExpander, self).__init__('add', 'source_to_target') TypeError: __init__() takes from 1 to 2 positional arguments but 3 were given HOT 1
- Dateset Error HOT 2
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 graphcl.