Closed Andylijinpan closed 1 year ago
Hi @Andylijinpan,
The pseudo labels on train set do not use extra CRF after irn. Your result (68.X) looks like no problem.
@chenqi1126 谢谢你的回答,大佬。 对于irnet后的训练集结果68.x,我担心我这个结果通过deeplabv2训练完可能达不到和你的结果一样高,我的这个结果真的可以吗?
@chenqi1126 另外,大佬方便给一下后半段v2训练的代码吗,我好直接用你的权重
利用伪标签训练全监督模型的代码是直接使用现有项目,你可以在readme里面找到,只需要修改路径就可以运行。
利用伪标签训练全监督模型的代码是直接使用现有项目,你可以在readme里面找到,只需要修改路径就可以运行。 谢谢您的回答
Hello, I want to use the pseudo-label after irnet training to train the fully supervised model of v2, is it the path to replace the real dataset with pseudo-label
Because the result I reproduced (after irnet processing), the Miou of train is 68. X, and the result of cam is consistent with your 58.5