Skip to content

fix: resolve training issues with ModuleNotFoundError and indices device mismatch #11

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
gxy2314 wants to merge 2 commits into
base: main
Choose a base branch
from
Open

fix: resolve training issues with ModuleNotFoundError and indices device mismatch #11

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
727b82d
fix: resolve training issues with errors
gxy2314 Dec 26, 2024
a249870
resolve training issues with mistakes
gxy2314 Dec 26, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,15 +1,15 @@
# Graph Convolutional Networks for Text Classification in PyTorch
# Simplifying Graph Convolutional Networks in PyTorch (TextSGC)

PyTorch 1.6 and Python 3.7 implementation of Graph Convolutional Networks for Text Classification [1].
PyTorch 1.6 and Python 3.7 implementation of Simplifying Graph Convolutional Networks [1].

Tested on the 20NG/R8/R52/Ohsumed/MR data set, the code on this repository can achieve the effect of the paper.

## Benchmark

| dataset | 20NG | R8 | R52 | Ohsumed | MR |
| dataset | 20NG | R8 | R52 | Ohsumed | MR |
|---------------|----------|------|--------|--------|--------|
| TextGCN(official) | 0.8634 | 0.9707 | 0.9356 | 0.6836 | 0.7674 |
| This repo. | 0.8618 | 0.9704 | 0.9354 | 0.6827 | 0.7643 |
| This repo. | 0.8605 | 0.9743 | 0.9384 | 0.6828 | 0.7728 |

NOTE: The result of the experiment is to repeat the run 10 times, and then take the average of accuracy.

Expand All @@ -32,4 +32,4 @@ NOTE: The result of the experiment is to repeat the run 10 times, and then take
3. Training model, run `trainer.py`

## References
[1] [Yao, L. , Mao, C. , & Luo, Y. . (2018). Graph convolutional networks for text classification.](https://arxiv.org/abs/1809.05679)
[1] [Wu, F. , Zhang, T. , Souza, A. H. D. , Fifty, C. , Yu, T. , & Weinberger, K. Q. . (2019). Simplifying graph convolutional networks.](https://arxiv.org/abs/1902.07153)
Loading