How to retrain model in graph (.pb)?

Question

I have model saved in graph (.pb file). But now the model is inaccurate and I would like to develop it. I have pictures of additional data to learn, but I don't if it's possible or if it's how to do it? The result must be the modified of new data pb graph.

score 3 · Answer 1 · answered Jul 17 '18 at 14:10

3

It's a good question. Actually it would be nice, if someone could explain how to do this. But in addition i can say you, that it would come to "catastrophic forgetting", so it wouldn't work out. You had to train all your data again.

But anyway, i also would like to know that espacially for ssd, just for test reasons.

answered Jul 17 '18 at 14:10

AlienBuster

73
4

What experience did you have with Deep Speech and catastrophic forgetting? Where you trying to do transfer learning? – Andres Felipe Jul 23 '20 at 05:55

score 1 · Answer 2 · answered Jul 17 '18 at 14:36

The mozzila/DeepSpeech community has contributed a way to initialize training from a frozen graph(.pb). It does not restores optimizer parameters, so adjusting the learning rate is necessary.

You could find the code at:

https://github.com/mozilla/DeepSpeech/blob/master/DeepSpeech.py#L1562

Hope this helps!

How to retrain model in graph (.pb)?

2 Answers2

Linked