Issue about AI explainability for TLT classification models

Hello.

I would like to realize the how TLT classification models make prediction by CAM or Grad-CAM

However. It seems that there is no infomation about AI explainability for TLT classification models.

How could I do to generate heatmap for TLT classification models by combining CAM or Grad-CAM ?

Thank you for your help in advance.

1 Like

TAO did not provide info for CAM or Grad-CAM. User can leverage other visualization instead. Refer to Visualizing Training - NVIDIA Docs