How to manage model file, when load more than 2 models downloading mannually from Tensorflow Hub?

Question

I tried to download model from the url It showed error: URLError: <urlopen error [Errno 101] Network is unreachable>

and solved this problem with How to load TF hub model from local system

But there are too many model files and all need to be called like saved_model.pb Is any better way to manage these files?

Hope there is a tree or real project structure suggestion. Thank you all!

Answer 1

Internally, TF Hub library (hub.load) automatically downloads models from tfhub.dev into the local TEMP directory. To enable downloading of multiple models, each model is placed into a directory corresponding to that models name (e.g. /tmp/hash()/). You could consider adopting a similar structure in your case.