Taehun Kim

Hi, thank you for your comment. Images in the ETIS dataset are more high resolution than other datasets, including training dataset. I think that's the reason why it shows lower...

See #12

Hi, thanks again for your interest. As I mentioned at the end of the readme, it is brought from the PraNet repository. Also, it is pre-trained with ImageNet 1K dataset.

I think you are right. Thank you for letting me know. I'll keep in mind this in my future works.

I'm not planning to since this isn't our main contribution, but thanks for letting me know that the authors of CaraNet seems to be using our code without any citation....

I just noticed that the author of [CaraNet](https://github.com/AngeLouCN/CaraNet/) updated their [readme](https://github.com/AngeLouCN/CaraNet/commit/e8895258282a1b82808fbe73f2de07f1e2565a2d).

Hi, thank you for asking. python - 3.6 tensorflow - 1.12 (cuda 9.0) pyyaml - 5.1 networkx - 2.2 Hope this helps!

Hi, graph_generator.py generates random graph. You can choose from watts strogatz, erdos renyi, or barabasi albert model. While running train.py, it generates random graphs when there are no graph data,...

Those are algorithms for ramdom graph generation. You can refer to the paper "Exploring Randomly Wired Neural Networks for Image Recognition"

I'm sorry but I'm little bit confused. Is your question about "dataset_generator.py"? or "graph_generator.py" .