How to add a preprocessing layer to a pretrained caffe model?

Question

I have a pre-trained image classification model saved in caffe, the model is expected to get grayscale(one channel) images. I want to use this model in a tool that only provides input of RGB(three channels) to the model. It is not possible to change the way this tool provides images so I thought of adding a layer before the input layer that transforms the input to one channel only, is that possible in caffe? and how?

I'm looking for a solution that doesn't require to define new layers to caffe if possible.

Note that I have the ".prototxt" and the ".weights" files of the model.

I previously did a similar thing in tensorflow but I don't know if this is possible in caffe and didn't find much material online.

Shai · Accepted Answer · 2022-08-10T11:52:29.177

1

You can add a Python layer to do it for you.

What is a Python layer. An example of such a layer can be found here.

edited Aug 10 '22 at 11:52

answered Aug 10 '22 at 10:33

Shai

111,146
38
238
371

Could you elaborate more please? maybe with a simple example if possible. – subspring Aug 10 '22 at 11:02
@subspring does your caffe veraion supports Python layers? – Shai Aug 10 '22 at 11:30
1

I checked the links .. seems like they should work for me. Thanks! – subspring Aug 11 '22 at 05:37

How to add a preprocessing layer to a pretrained caffe model?

1 Answers1