Using Class Activation Maps (CAM) for visualization

(Arka Sadhu) #1

I wrote a small notebook on how to go about visualizing CAM here

It also covers when you have a hidden layer after the Adaptive Concat Pooling. Grad-CAM work is still in progress.


(Benoit) #2

Thank you @TheShadow29 I use your code to do the same things with ResNext50 :

(Arka Sadhu) #3

Nice. I will add a link to this in my repo as well :slight_smile:

(Bumblebee) #4

Hi @Benoit_c / @TheShadow29 ,

I have one query regarding class activation maps. If i have a trained model which was initialized using convlearner.pretrained. Now i can load the saved model replace the last layers as per cam and then train the last layers. Is this okay ? or the idea is to retrain the whole network with modified last layers? looking forward to your response.


(Arka Sadhu) #5

I am not sure unfortunately. I think you can use grad-cam instead of replacing the last layers.

(Bumblebee) #6

ok. cool. Thanks for prompt response. So need to do a small poc on that part. @Benoit_c any thoughts on this?

Apart from that have you been able to do a small poc on Grand Cam ?

(Benoit) #7

Hi, sorry, I have to retrained the whole model. It will be better if we could visualize an existing model…