Allen
Allen
The calculate is a little bit slow, is there some method to speed it up? Can I use GPU instead of CPU?
Hi, thanks for your wonderful implement by PyTorch. I have a question why does the node feature use an all 1 tensor(shape: (29426, 29426)) rather than one-hot? 
Hi, thanks for your wonderful job. But I encounter confusion about the data loader function. Detail as below: ``` python parser.add_argument('--data_path', type=str, default='data/20ng', help='directory containing data') ``` 1. I can't...
I read the codes and maybe it's for only two views. So, How can it be used for more than two views datasets?
你好,很抱歉来这个下面留言,因为我没能找到[Short Text Classification via Knowledge powered Attention with Similarity Matrix based CNN] 对应文章的repo,请问可以上传下该文的代码吗?万分感谢!
the sample dataset 20news takes a small vocabulary size of 1995, therefore, the adj becomes a 1995*1995 tensor. But if I make a larger vocabulary size, the adj matrix will...
``` OS: Linux Debian 10 ``` ``` uncaughtException AssertionError [ERR_ASSERTION]: 400 != 400 at Object.notEqual (/app/node_modules/wechat4u/src/util/global.js:63:14) at /app/node_modules/wechat4u/src/core.js:108:16 at processTicksAndRejections (node:internal/process/task_queues:96:5) { code: 2, details: 'AssertionError [ERR_ASSERTION]: 400 != 400\n'...
OS: ubuntu-16.04 Nodejs: 19 