Draw a Shape or Load a Sample
Grad-CAM Overlay
How Grad-CAM Works: Gradient-weighted Class Activation Mapping computes the gradient
of the predicted class score with respect to the final convolutional layer's feature maps.
These gradients are averaged to get importance weights, which are then used to create a weighted
combination of the feature maps, producing a heatmap showing which regions most influenced the prediction.
Load Sample Shape
Training
Network Status
Training Epoch:
0
Training Loss:
-
Accuracy:
-