GradCAM's heatmap worsened from .1 to .2
TedGraham opened this issue · 1 comments
TedGraham commented
I'm using Keras' VGG16 to classify a picture of a dog and am generating a heatmap from GradCAM.explain.
Using .1.0 and specifying the layer_name of "block5_conv3" gives a much nicer heatmap (first image) than using .2.0 and not specifying the layer_name (second image).
- the behavior of .2.1 and .2.0 appears the same to me
- specifying the layer_name with .2.1 doesn't fix this, the auto choosing of the layer appears to be picking the block5_conv3 layer
RaphaelMeudec commented
Thanks for raising this, will look into it!