rules for pyramid_level_inputs?

[innat]

Current Behavior:

While trying to get P1, P2, P3 from EfficientNet, I got

backbone = EfficientNetV1B0Backbone(input_shape=(512, 512, 3))
for k, v in backbone.pyramid_level_inputs.items():
    print(k, v, backbone.get_layer(name=v).output)

P1 block1a_project_activation <KerasTensor shape=(None, 256, 256, 16) >
P2 block2b_add <KerasTensor shape=(None, 128, 128, 24) >
P3 block3b_add <KerasTensor shape=(None, 64, 64, 40) >
P4 block5c_add  <KerasTensor shape=(None, 32, 32, 112) >
P5 top_activation  <KerasTensor shape=(None, 16, 16, 1280) >

Expected Behavior:

For P5, I think it should be from block7a_project_activation, before the top activation. This will give (None, 16, 16, 320) instead of (None, 16, 16, 1280) - which can be used in EfficientDet model.

Also, the P3, P4, no hard opinion, but wouldn't it be more better to pick tensor from project_activation layers?

[sachinprasadhs]

HI, Could you please try this in Keras Hub package, for all the pyramid level type of models we have a FeaturePyramid task for these backbones now.
If you still have any question, open a new issue in /keras-hub repo