I am trying to deploy a desktop application with Tensorflow (with Python and Briefcase), but the installed wheel has almost 900MiB on disk. Are there ways to make this lighter?
I experimented erasing the entire
/includesubdirectory, which saved more than 100 MiB, apparently without ill effects. Will that explode in my face later on? I’m also considering deleting
/lite, gaining another 15 MiB.
More than half the space is occupied by a single file,
_pywrap_tensorflow_internal.so, at 515 MiB. Is there any way of making this smaller (maybe recompiling Tensorflow from the source with custom options?)
The only other “obvious” candidate is another binary,
_pywrap_tfcompile.so, at 58 MiB. I removed it without immediate effects. Will that explode in my face later?