为什么按照作者提供的代码训练之后，无法达到实验结果？

[helix333111]

以 resnet-v2 为backbone，split=0， epoch = 200 , 训练之后的结果远没有达到 mIoU 61.7（ pascal 5i 1shot fold 0）?

作者提供的模型可以达到61.7 ，是不是epoch 为200太少了，还是batch size 为4 太小了？

我的训练结果只有 mIoU 接近 50

请教各位同学。

[tianzhuotao]

@helix333111
Hi, thanks for your interest.

You can take reference from this issue:

#6

We only use 1 GPU to train our model on PASCAL, and different Pytorch versions may cause different results.

Thank you.

[tianzhuotao]

@helix333111

If you have any further questions, feel free to re-open this issue.

Thank you~

[helix333111]

Thank you !!