Compression speed is around 2 KB/sec.
Apologies if this is a noob question, but could you improve it with training?
Apologies if this is a noob question, but could you improve it with training?
Considering all other things like GPU, code quality etc. equal, the speed here mainly depends on the size of the network. Larger networks result in better performance (logarithmic), but also slower speeds (linear). There are some tricks like pruning to create significantly smaller networks with similar-ish performance, but good models are often large.
Unrelated to your question, what nobody mentions is that the decompression side also needs to complete network. With 57M and 187M parameters, those files are going to be quite large, > 100MB for sure. That completely annihilates the performance wins for 1 time transfers.
https://news.ycombinator.com/item?id=27244810
it's a very clever use of symmetry.
LZ78 used it "just" to build a dictionary, but the general idea of using symmetry is there.
(A fascinating variant on this is Semantic Dictionary Encoding, by Dr Michael Franz in his doctoral dissertation (1994), that used this symmetry to compress partial ASTs to cache partially generated code for runtime code generation)
As I understand it, when starting up (beginning of stream) - the network does not compress, then guesses the next byte at every turn determininstically from input so far.
Decoding can "read" the fist byte, then proceed to learn and guess the second byte and so on.