xiaozhen228

How does SAM solve the problem of catastrophi forgetting problem?

1

How does SAM solve the long-term learning problem? That is, what methods he would take to overcome catastrophic forgetting.

自然景物数据集

2

作者你好，我在两类自然景物数据集上使用sam_lora_image_encoder.py 的分割效果非常不好，会把所有的前景预测为背景，但是使用sam_lora_image_encoder_mask_decoder.py 的效果虽然不是特别优秀，但是有一定的效果。我的理解前者是对mask_decoder中所有参数进行了微调，理论上效果应该更好，后者用lora微调了mask decoder，效果会差点。但是现在使用sam_lora_image_encoder.py 基本没有效果，请问您有啥建议吗？理论上sam_lora_image_encoder_mask_decoder.py上有效果(iou:0.6)那么说明我的数据集预测处理应该没有啥问题

How do I change my own data set? Do I just need to change the number of categories and the routing of the data set j? This calculates the IOUs...

Implemented a housing price prediction case

1

18200100199 屈震

Implemented a mnist classification with ResNet

1

18200100199+屈震