google-deepmind / google-deepmind/c3_neural_compression
Entropy coding the latents
Open
- Dominant language
- Python
- Stars
- 101
- Forks
- 10
- PR merge metrics
- No merged PRs in 30d
Description
Dear authors,
Thank you very much for open-sourcing this work.
In Appendix B.3 of the paper, it is mentioned that you have used range-coder to encode the learned latents. I am not able to find that implementation in the current code. Moreover, I am curious to know if a range-coder independent of the ARM probability model pψ. Thanks in advance.
Contributor guide
Assessment
This issue has not been assessed yet.