NaiKang Zhong

About the effects of IRPE

3

The IRPE project is a very good initiative. Currently, I have applied IRPE and observed improvements in the model. However, I have noticed that when I solely apply positional encoding...

Why can I obtain correct results during inference, but during training, I can only achieve a MAP (Mean Average Precision) of 3.7

Why can I obtain correct results during inference, but during training, I can only achieve a MAP (Mean Average Precision) of 3.7

你好up主，很感谢你能出这期视频，视频中说到的如何去用自己的模型生成gradcam我是理解的，但是我有个疑问是，我的改进的模型是Resnet101后面接了Transformer做的多标签图像分类，那么为我的fc.weight层在transformer后面，但是我的目标层是resnet101的最后一个卷积层，这样合理可实施嘛，希望up主有时间能够回复我，非常感谢！