Grad-Cam from ONNX model #668
Description
Feature Request
Ability to get subset of layers from a list of layers for a given model
What is the problem that this feature solves?
I'm interested in implementing Grad-CAM starting with an ONNX model and from my understanding, importing onnx saves each layer as an attribute of the model struct but there's no way to get a subset of the model other than rebuilding it manually.
Describe the feature
Why is this feature necessary? What does it accomplish?
Relevant Model Zoo feature areas
Which area in the Model Zoo infrastructure does this impact?
explainable AI, computer vision, backbones
Notes
Fairly new to burn and I'm excited to use it!