Last Friday, my advisor asked why the entropy coding in my encoding method took twice as long as another method. My intuitive understanding was that his method optimized the C++ library for entropy coding, rather than directly using the entropy coding provided by CompressAI.

So yesterday I spent a whole day adapting the entropy coding part of my method to his optimized entropy coding. I found that the entropy coding speed was exactly the same! ＞﹏＜

Today I spent another day looking for the reason, analyzing from multiple angles such as whether the bpp was similar, why the entropy coding in my method was slower. The result!! The result is that the amount of data input to my entropy coding is more than three times his!

Damn it, my two wasted days.