Hi,
When we:
- fit with a pre-trained model
- save
- unfreeze
- fit
- load what we saved in step 2,
are we overwriting the weights/activations on the final layers with the saved version? I mean, do we end up with:
- weights on the final layers according to the fit from step 1; and
- weights on the earlier layers according to the fit from step 4?
The weights we get at the end of step 5 is not the same as that we got at the end of step 1, correct?
Thanks!