Closed luckybeanss closed 4 years ago
Hi @luckybeanss, hyper-parameters are either mentioned in the paper or included in config.py
. May I know which hyper-parameters are missing? Thank you.
By the way, if the performance gap is less than 0.5 mIoU, it could be due to randomness.
Best regards, Kaixin
Thanks for your reply. According to the parameters in the code and paper, the 1-shot accuracy I got on the PASCAl-5i dataset is 41%. So I want to know which parts need to pay attention。
@luckybeanss you mean the mIoU averaged across 4 splits is 41% or just the first split?
@kaixin96 How can I run your code with two GPU cards when the batch_size is set to 4 for fast training ? Could you provide the corresponding modifications and run command ?
Hi @qiulesun, as your question is not relevant to this issue, can you open a new one? It will be easier for other people to search similar questions. Thank you.
I got lower accuracy too. About 41% for 1-way 1-shot trained with default settings in the code, 47% for 1-way 5-shot using trained VOC_1way5shot_set3 model, is there any hyper parameters needed to be modified for default setting ?
Hi @tymatfd, the performance reported in the paper for "1-way 5-shot split-4" is 46.5, which is close to your result. Note that set_3 actually refers to split-4 in the paper. Hope this clarifies your question.
Thank you.
Ah, Thank you very much @kaixin96 . So the accuracy of model trained with default settings is actually calculated on split-1 ? which is reported to be 42.3
You are right. The configuration for the split is in https://github.com/kaixin96/PANet/blob/1695bf37c2f7585323e09cfcfb3bef8d4fff1b86/config.py#L37
Thank you.
I’m closing this issue because it has been inactive for a while. Feel free to reopen if you have questions. Thank you.
Thanks for sharing your code. It is a really great work! But the accuracy rate I got based on this code is lower than that reported in the paper. Can you share the hyperparameter settings on the VOC2012 dataset?