Save transfer learning weights to cache file

vision
1

hi,
how do i save inception model transfer learning weights to cache file for reuse. i need use it for second LSTM model.
Thanks

2

You could save the state_dict following the serialization semantics.
Would that work for you or what kind of cache would you like to use?

3

i need use final dense layer 2048 elements save as vector for fast access.it uses as initial state for LSTM(h0).

4

I assume you are not running both models in the same script?
In that case, you could just store these features using torch.save and load them for your LSTM using torch.load.

5

Yes. of course, i am using it separately. Thank you