Model._modules[] to find a layer

1

I’ve trained a DenseNet121 model, and am trying to get ahold of one of the final layers for a GradCAM implementation. The implementation uses model._modules[] as a dict from layer name to layer, but for some reason, my model has only one key-value pair in this dict: “module” to the entire DenseNet object. What should I do instead? My version is 1.2.0.

Thanks!

2

Which layer would you like to get?
This code would index a specific conv layer inside the model:

model = models.densenet121()
model.features.denseblock4.denselayer2.conv2

Your mentioned method is an internal method and thus shouldn’t generally be used.

3

I’m looking for the a layer to create class activation maps, so probably one of the last ones like “module.densenet121.features.denseblock4.denselayer16.conv.2” or “module.densenet121.features.norm5”

4

So would the approach of directly accessing the modules work or are you still stuck?

5

My model is wrapped in torch.nn.DataParallel(model). How do I get “under the hood” to access the Densenet? I think this is probably the issue with the first part of the issue

6

You could access the model via model.module.features...

7

Oops! silly mistake on my part. Appreciate it!

8

what about Sequential, getting AttributeError: ‘Sequential’ object has no attribute ‘module’.

9

The .module attribute will be added by nn.DataParallel for all models including nn.Seuqential:

model = nn.Sequential(
    nn.Linear(1, 1),
    nn.ReLU(),
    nn.Linear(1, 1))

model = nn.DataParallel(model)
print(model.module)
> Sequential(
  (0): Linear(in_features=1, out_features=1, bias=True)
  (1): ReLU()
  (2): Linear(in_features=1, out_features=1, bias=True)
)
10

I am working on classification of five different types of images of skin and I trained the AlexNet model and GoogleNet Model. Now I wanted to implement the Grad-CAM on the final layer of the these models and want to get the heat-map.

after reading many blogs and coding material I reach here. This code is specifically use resnet50 model.

model = models.resnet50(pretrained=True)
grad_cam = GradCam(model=model, feature_module=model.layer4, \
                   target_layer_names=["2"], use_cuda=args.use_cuda)

How should I pass the feature_module and target_layer_names to constructor of the grad_cam class for AlexNet and for GoogleNet.

I realized I need to get the final layer from the Pretrain Network by using the following code.

 new_classifier = nn.Sequential(*list(model.classifier.children())[:-1])
 model.classifier = new_classifier

How can I use this way to pass as parameter to the grad_cam class.