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

[hwasiti (Haider Alwasiti)]

Yeah, with preliminary search in the forum I have found your nb but did not tried it yet from your post here:

How can one remove the pooling from pretrained model?

You can actually do this using nn.Sequential quite easily. Have a look at my notebook: https://github.com/TheShadow29/FAI-notes/blob/master/notebooks/Using-Pretrained-Pytorch-Models.ipynb. Specifically, get the pretrained model using md = learn.model. Print the model, keep the model till before the max pool. After that add a custom head. Suppose the max pool is at layer -5, you can do new_md = nn.Sequential(*list(children(md))[:-5], custom_head). custom head basically includes everything you wo…

I wanted to try it before posting the link to your post here…
Your nb seems helpful! Thanks…

Custom_head and xtra_cut will be taught in part2 ? Do you remember which lesson exactly?