how can i use my own weight_pth?

[zdj97]

thanks to your work for grad-cam!
however how can i use my own weight_pth to product the grad-cam images?

[Kazuto Nakashima]

Please create your own code like demo3.

1. Determine the layer where you want to visualize activation maps.
   You can see the available layer names from your weights, e.g., print(*your_weights.keys(), sep="\n").
2. Determine the class id to compute gradients.
3. Create a GradCAM instance with your model.
4. Then forward(), backward(), generate().

[Khaldon Minaga]

Hi, can you expound on number 3 & 4? @kazuto1011

[JanineCHEN]

Thanks a lot for the repo, having same question here, could you kindly elaborate step 3 & 4? @kazuto1011
Thank you in advance.

[Kazuto Nakashima]

Suppose you have the model which returns logit in (num_batch, num_class) shape.
Then please create the Grad-CAM instance with the model.

gcam = GradCAM(model=model)

The GradCAM class has three principal method forward, backward, and generate.

First, please call forward with batched images, then you get class probabilities and the corresponding indices in descending order. At the same time, gcam saves the intermediate feature maps.

sorted_probs, sorted_ids = gcam.forward(images)

Here we take indices of the top 1 classes for example.

top1_ids = sorted_ids[:, [0]]

Please call backward with the indices. This line computes and saves the class-specific gradients at all layers.

gcam.backward(ids=top1_ids)

Now, gcam has {feature map, gradient} pairs of all layers.
Finally, please call generate with the layer name you want to visualize.

regions = gcam.generate(target_layer='any_layer_names')