Austinzhenghua

Results 17 comments of Austinzhenghua

yes, I have cuda 11.1 ![image](https://user-images.githubusercontent.com/34674970/174997580-10adc742-0280-4805-a53a-79c63a788467.png)

But it seems `python setup.py build_ext --inplace` the setup.py can not find my cuda. do you think is their any problem with my bashrc? ![image](https://user-images.githubusercontent.com/34674970/174998373-45b18b52-35a7-49d1-a816-ac2274b69a4e.png) thank you so much!

have tried but no use. ---- Replied Message ---- From

Hi, I have a question about the dataset. If I have my own data but not graph data. Can I use KNN to construct some r ego network to instead...

I use KNN for each data point to construct N subgraph or just use one time to construct a graph? hua zheng ***@***.*** 签名由 网易邮箱大师 定制 On 06/30/2021 02:07, Yuning...

So I should construct the graph data same format like the TU dataset? the raw data have many documents as far as I know. Thank you for your kind help!...

> please follow this repo to prepare the dataset. > > https://github.com/graphdeeplearning/benchmarking-gnns Thank you very much!

Thank you so much, I found the reason is that, there are no __init__ files in each package. Another problem is when I run main_superpixels_graph_classification.py I got : I] Loading...