search

kedartatwawadi / NN_compression

MIT License
213 stars 42 forks source link

Where's the Arithmetic Coder Block? #6

Open yuzefang96 opened 6 years ago

yuzefang96 commented 6 years ago

I didn't find the source code for the arithmetic encoder&decoder, did I miss them?

kedartatwawadi commented 6 years ago

In the current version, I have not included Arithmetic coder, as the compression performance obtained by arithmetic coder is exactly equal to the log-loss value obtained at the end. (See: https://web.stanford.edu/~kedart/files/deepzip.pdf, Sec 2.3)

kedartatwawadi commented 6 years ago

Will work on adding the arithmetic encoding/decoding block support soon

suikammd commented 6 years ago

@yuzefang96 Hey， do you get the expected results as the author provided? I tried several times but couldn't achieve it. I major in electronics and I want to make it work on FPGA. Will you kindly share your training tips?