IoU Loss should only reduce over 1 axis by default.

[LukeWood]

Keras losses reduce over one axis by default - currently IoU is reducing over two. This will make it impossible for us to mask out background boxes. To get around this, we should only reduce over one axis instead of two in IoU loss.

This means that after the IoU is computed you should have [batch_size, num_boxes] returned from the loss

[LukeWood]

@quantumalaviya

[sachinprasadhs]

Thanks for reporting the issue! We have consolidated the development of KerasCV into the new KerasHub package, which supports image, text, and multi-modal models. Please read the announcement. KerasHub will support all the core functionality of KerasCV.

KerasHub can be installed with !pip install -U keras-hub. Documentation and guides are available at keras.io/keras_hub.

With our focus shifted to KerasHub, we are not planning any further development or releases in KerasCV. If you encounter a KerasCV feature that is missing from KerasHub, or would like to propose an addition to the library, please file an issue with KerasHub.

[github-actions]

This issue is stale because it has been open for 14 days with no activity. It will be closed if no further activity occurs. Thank you.

[github-actions]

This issue was closed because it has been inactive for 28 days. Please reopen if you'd like to work on this further.