train from scratch

[MengXinChengXuYuan]

Did anyone try to train from scratch, without any pertained weight? I want to make the model adapt to my project, with 224 * 224 input, 8 * 8 patches and 6 sliding size, which means there is no pertained weight for me. I found it very hard to converge, after 10000 steps the train acc is still around 0.6 Than I tried the original training configurations, except loading pertained weight, the same issue Did I miss anything?

[qing-xue]

Hey, I got the same problem, and my best acc is just 0.8.

[bjtuln]

I got the same problem