Comments (10)
Hi! This variable is assigned by the previous step, i.e., 'Node Attributes' in function brain_graph. You can check whether it runs normally.
Anyway, this part is to check if the downloaded data files have the same columns, and you can safely delete this checking part (line 106 to 111) as I have already done so. Or, you can assign variable 'file_path' to an arbitrary file's path, e.g., file_path=os.path.join(data_folder, files[0]), before the line 107 in brain_graph. Thanks!
from asd_gp_gcn.
from asd_gp_gcn.
thank you. I will try it.
…
---Original--- From: "Li @.> Date: Wed, Mar 2, 2022 22:41 PM To: @.>; Cc: @.@.>; Subject: Re: [jhonP-Li/ASD_GP_GCN] error (Issue #2) Hi! This variable is assigned by the previous step, i.e., 'Node Attributes' in function brain_graph. You can check whether it runs normally. Anyway, this part is to check if the downloaded data files have the same columns, and you can safely delete this checking part (line 106 to 111) as I have already done so. Or, you can assign variable 'file_path' to an arbitrary file's path, e.g., file_path=os.path.join(data_folder, files[0]), before the line 107 in brain_graph. Thanks! — Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android. You are receiving this because you authored the thread.Message ID: @.***>
I comment out the this checking part (line 106 to 111) . And run download_ABIDE.py. When i run main.py, there is a new error.
Traceback (most recent call last):
File "/home/xxx/PycharmProjects/xxx/main.py", line 33, in
graph_pooling(args)
File "/home/xxx/PycharmProjects/xxx/training.py", line 28, in graph_pooling
abide_dataset = TUDataset(args.data_dir, name='ABIDE', use_node_attr=True)
File "/home/xxx/anaconda3/envs/xxx/lib/python3.7/site-packages/torch_geometric/datasets/tu_dataset.py", line 69, in init
super().init(root, transform, pre_transform, pre_filter)
File "/home/xxx/anaconda3/envs/xxx/lib/python3.7/site-packages/torch_geometric/data/in_memory_dataset.py", line 57, in init
super().init(root, transform, pre_transform, pre_filter)
File "/home/xxx/anaconda3/envs/xxx/lib/python3.7/site-packages/torch_geometric/data/dataset.py", line 88, in init
self._process()
File "/home/xxx/anaconda3/envs/xxx/lib/python3.7/site-packages/torch_geometric/data/dataset.py", line 171, in _process
self.process()
File "/home/xxx/anaconda3/envs/xxx/lib/python3.7/site-packages/torch_geometric/datasets/tu_dataset.py", line 138, in process
self.data, self.slices = read_tu_data(self.raw_dir, self.name)
File "/home/xxx/anaconda3/envs/xxx/lib/python3.7/site-packages/torch_geometric/io/tu.py", line 37, in read_tu_data
x = cat([node_attributes, node_labels])
File "/home/xxx/anaconda3/envs/xxx/lib/python3.7/site-packages/torch_geometric/io/tu.py", line 78, in cat
return torch.cat(seq, dim=-1) if len(seq) > 0 else None
RuntimeError: Sizes of tensors must match except in dimension 1. Got 0 and 96681 in dimension 0 (The offending index is 1)
from asd_gp_gcn.
Hi! This variable is assigned by the previous step, i.e., 'Node Attributes' in function brain_graph. You can check whether it runs normally. Anyway, this part is to check if the downloaded data files have the same columns, and you can safely delete this checking part (line 106 to 111) as I have already done so. Or, you can assign variable 'file_path' to an arbitrary file's path, e.g., file_path=os.path.join(data_folder, files[0]), before the line 107 in brain_graph. Thanks!
After downloading, the raw data (i.e. fMRI) will be deleted.
And the raw data still exits. The processed folder is empty.
from asd_gp_gcn.
This is weird. I just rerun it, and the data (brain graph) is successfully saved to './data/ABIDE/raw'. Has this folder been created in your case?
from asd_gp_gcn.
This is weird. I just rerun it, and the data (brain graph) is successfully saved to './data/ABIDE/raw'. Has this folder been created in your case?
yes, there are five files. ABIDE_graph_labels and ABIDE_node_attributes are empty. others are not
from asd_gp_gcn.
Hi! I have cloned this repository but cannot reproduce your case. The files of attributes and labels are not empty. If you still have not fixed it, please provide more information about your modifications to our code. Thanks!
from asd_gp_gcn.
Hi! I have cloned this repository but cannot reproduce your case. The files of attributes and labels are not empty. If you still have not fixed it, please provide more information about your modifications to our code. Thanks!
this is because i can't download the abide successfully. i have the same problem with others' repo. and i haven't solved the problem. thank you.
from asd_gp_gcn.
OK. The ABIDE preprocessed dataset is available at: https://s3.amazonaws.com/fcp-indi/data/Projects/ABIDE_Initiative. You can look at function fetch_abide_pcp of nilearn (https://nilearn.github.io/modules/generated/nilearn.datasets.fetch_abide_pcp.html), or you can directly download the dataset through the URL by some tools like Cyberduck. If these also do not work, maybe you need a VPN. Good luck!
from asd_gp_gcn.
from asd_gp_gcn.
Related Issues (5)
- Graph pooling and LR HOT 1
- Accuracy HOT 7
- TUDataset- HTTP Error 404 HOT 1
- Accuracy problem HOT 3
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 asd_gp_gcn.