Use pretrained model with less classes to start training a model with more classes

[Claus (Claus Trost)]

Hi,

I had a look how to do this:
Check out this thread:

How to remove the last fully connected layer from a CNN in fastai to stack more than one CNN into a FC-NN?

There are ML problems when we need to stack more than one model. Take for example chest X-Rays need stacking 2 CNNs for front and lateral views like this model : [ScreenClip] Source The above method is way better than stacking 2 full CNN into FC (which is I am aware it is doable with fastai) like this: [ScreenClip] Because the output of each CNN in the 1st image has way more features describing each xray image, which is crucially important… Since the physician will not be able to classif…

This should problably help you.
I think the code of post in particular should be able to do it, and it even has a working example:

How to remove the last fully connected layer from a CNN in fastai to stack more than one CNN into a FC-NN?

You can just get a list with the required model and add a custom head. Say you want to remove the last layer and replace it with new custom head learn.model = nn.Sequential(*list(children(learn.model))[:-1], custom_head). Have a look at this: https://github.com/TheShadow29/FAI-notes/blob/master/notebooks/Using-Pretrained-Pytorch-Models.ipynb as well.

Please tell us if it worked out for you!
BR
Claus