CAM using InceptionResnetV2

[ghost]

Hi Cadene, Thanks a lot for providing these models. I am relatively new to PyTorch I am finding it difficult to generate Class Activation Maps for my trained model (InceptionResnetV2) on XRay images.

When i see some tutorial, I observe the following:

self.feature_extractor = model.module.densenet121.features
self.feature_extractor.eval()
self.classifier = model.module.densenet121.classifier

So here, type(feature_extractor) is torch.nn.modules.container.Sequential as the above code is for Densenet model taken from pytorch vision library. How do I generate features and classifier as the above code for InceptionResnetV2 from Pretrainedmodels?