How to deploy a trained model in Python 3.5 environment?

I need to deploy a model I trained in our environment which is Python 3.5 and I can’t upgrade the Python without affecting 10 other people’s previous work. So my options now are:

  1. modify to work in Python 3.5 (not sure how much work it is)
  2. save model as a pytorch model (*.pth):
    Tried, but learner.models.model are Sequential, which do not have a save method for
  3. save model (*.h5) and load it in pytorch:
    Seems that I need to reconstruct the model before loading it.
  4. other methods.

Any suggests may help greatly.
Thanks for reading!

1 Like

Just a follow-up, I tried #1 and it turns out the amount of work is small, just change every f’’ format string into older form seems to work. Hope I didn’t miss any other Python 3.6 only features.

I am interested in the 3rd option. Keep us posted

Follow up on 2, turn out this is really simple:

model = learn.model, 'my_model')

That’s it, then it can be loaded in pytorch with

model = torch.load('my_model')

Just remember to use


for inference. (thx @cedric for correction)

1 Like

Do you mean “for inference”?

ops. typos. thx.

Oh I forgot to mention things like image normalization could be different for different models, so will need to take care of. And also data.classes has to be stored and read. After all these, one gets more appreciate the convenience of, which gets these details right for you behind the scene.

Thankyou for sharing this finally my project is now ready
credit :