Han Hu

Thanks @guozhiyao

> Hi Niels and Hugging, We are happy to be part of it. Please let us know if you need our assistance in the future maintenance. Thank you! Best, Han...

> Can you please provide more information, for example, your loss function, training configuration, loss curves, etc?

Thanks for point out these issues @HC-2016 . We will fix both of them.

@feiyangsuo Yes, ape is set False by default, where we find ape has no benefit to general vision recognition problem. If you want to use this feature, you can initialize...

Yes, we used bicubic interpolation.

> > > > hi how load modify the pretrained model of input size 384 to finetune the input 448 when load model ? bicubic also

You can try accumulate gradients to enlarge your batch size from 64 to 1024. Will provide configs for finetuning from ImageNet-21K to ImageNet-1K.

Can you share the concrete question about apex?

We have not tried human pose estimation