Erasing-Attention-Consistency
Erasing-Attention-Consistency copied to clipboard
zyh-uaiaaaa
Changing backbone to ResNet-18
'Changing backbone to ResNet-18 should first tune the learning rate in order to acquire high classification accuracy. More details can be found in the closed issues.' 您好，我浏览了下关闭的问题没有找到相关的内容。当更换backbone后，相关学习率该怎样调整呢？
请问为什么我直接使用您提供的代码，模型结构方面没有做任何修改，并直接使用了链接中提供的ResNet50的预训练模型，在clean标签上训练得到的测试集的最好结果仅为82%左右?
学习率需要从1e-4调整到2e-4。 这个不太可能，估计是你代码某个地方出了问题，或者标签没有读对，82%的准确率过于低了。 你可以参考一下我对其他人问题的回复，如下： “I have re-run my code without making any changes. Using the pre-trained ResNet-50 model, it easily achieved an accuracy of 90.35% and the best accuracy recorded was 90.51%, without any label noise. Could you please either re-run my code or provide me with your log file to assist me in identifying the reason behind this?”
