search

larq / compute-engine

Highly optimized inference engine for Binarized Neural Networks
https://docs.larq.dev/compute-engine
Apache License 2.0
243 stars 35 forks source link

TF lite converter weight bitpacking #40

Closed Tombana closed 4 years ago

Tombana commented 5 years ago

Ideally we would like the TF lite converter to store the binary weights in a packed way so that the tflite model file stays small.

Another option might be that we write a tool ourselves that takes a converted .tflite model and does another pass on it, transforming the weights appropriately.

arashb commented 4 years ago

this is resolved in https://github.com/larq/compute-engine/commit/ef372f10cdb0edf6884c28cd873d2f3775470e2b