The problem encountered during training on my own dataset about softgroup HOT 4 OPEN

I have the same issue with my custom dataset!
I thought either the model was not proper for my custom datasets or I have not found the proper hyperparameters yet which causes sticking in a local minima! However, it is interesting that you have the same issue on your custom dataset.
@thangvubk Could you please possibly give an insight about it?

from softgroup.

Thank you for your work and sharing. I encountered an issue while training my own dataset. as shown in the figure. May I ask what could be the reason for this situation? I look forward to your response.

from softgroup.

您好：感谢您的工作和分享。我在训练自己的数据集时遇到了一个问题。我按照 S3DIS 数据集的示例构建了自己的数据集，该数据集包括两个语义类：stem 和 leaf。在训练第一个纪元和第 100 个纪元时，叶实例的精度评估保持不变。在这100个纪元中，叶实例的精度没有变化，而茎实例的精度略有变化，如图所示。请问造成这种情况的原因是什么？我期待着你的答复。

Hello, I'm glad to hear that our research directions are similar. I would be happy to exchange ideas and collaborate with you. Please feel free to provide me with your contact information, and I will be in touch. I look forward to our future discussions.

from softgroup.

Hello： Thank you for your work and sharing. I encountered an issue while training my own dataset. I constructed my own dataset following the example of the S3DIS dataset., which includes two semantic classes: stem and leaf. When training for the first epoch and the 100th epoch, the accuracy evaluation of leaf instance remains the same. There is no change in the accuracy of leaf instance throughout these 100 epochs, while there is slight variation in the accuracy of stem instance, as shown in the figure. May I ask what could be the reason for this situation? I look forward to your response.

@buggogogo : Hello, I was wondering if you were able to find the source of error for the accuracy issue?
I have the same issue and appreciate sharing your experience; Thanks

from softgroup.