ImageNet pre-trained HAT-L models without any fine-tuning.

[USTC-JialunPeng]

Hi, thank you for your great work! I want to test the performance of ImageNet pre-trained HAT-L models without fine-tuning on DF2K. When pre-training HAT-L on the ImageNet dataset, the training time is long (about 13 days using 8 V100 GPUs). Could you please release those ImageNet pre-trained HAT-L models without any fine-tuning? Thanks for replying!

[chxy95]

@USTC-JialunPeng I'm not sure if the files are still preserved. I will check it these two days.

[USTC-JialunPeng]

@chxy95 Thanks for your help！

[chxy95]

@USTC-JialunPeng BaiduYun access code: vacr

[USTC-JialunPeng]

@chxy95 Thank you！