How many iterations do you train to get the ade20k result

[Cheng Han]

Hi, I am curious on how many iterations are you training on ade20k result. I looked for Segformer paper using 160K iters to reach the performance of mIOU 37.4(MiT_B0). But I found you are using 40k to reach a competitive result (mIOU 37.2). Is that a typo or it is reaching a competitive performance with much less iterations? Also, could you provide the pretrained model for pvt_b0 to b5?

Thanks

[Cheng Han]

I understand that 8 gpu are applied instead of 4 in mmsegmentation, so lr*2 and max_iters/2. But I read the segformer as well, they are applying 8 gpu with 160k iters(from config). Which pretty impressed me to have such smaller number of iters to reach similar mIOU