FAN

FAN copied to clipboard

Thanks for your works. I noticed that the FAN-Hybrid-L model weights pretrained on ImageNet 1k is not available at the moment, will it be released in the future?

leoil

Why do the average results of Table 13 differ from the results of Table 9? Some methods are the consistent but not all.

ydhongHIT

Performance of FAN_tiny on ImageNet1K

5

Hi, congratulations on the cool work! One question about the code: when I train fan_tiny_12_p16_224 on IN1K, I got the clean accuracy of 77.454, lower than the reported 79.2. I...

bfshi

TianjinYellow

Hi~ Thank you for your outstanding contribution! Could you please open source or send me the script of clustering visualization in the paper? I need it very much. My Google...

stoor2kushidai