search

YaoleiQi / DSCNet

Pytorch Implement of Dynamic Snake Convolution (ICCV2023)
403 stars 36 forks source link

Can you share more training details? #15

Open ReginaYann opened 1 year ago

ReginaYann commented 1 year ago

Thanks a lot for sharing your code! Your conference paper shows that the dice coefficient of the baseline models and your proposed model both reached approximately 0.8. However, when I conduct the experiment, my model doesn't perform as well as yours. Would you like to share more training details? For example, did you use any pretrain weight models?

WHU-YH-jx commented 1 year ago

Me too, hope for more training details.

YaoleiQi commented 11 months ago

Thank you very much for your question. We did not use pre-trained parameters. If it's the DRIVE dataset, you can check the data usage and data augmentation. We have iterated and optimized the code and submitted it to some open-source repositories. If we successfully establish it in the future, we will notify you promptly. Regarding detailed code explanations and the training process, we will consider providing updates if we have the time in the future.