Ian Stenbit
Ian Stenbit
@LukeWood can you expand on the requirement here? Perhaps some example code demonstrating this need would be useful. I'm curious why we would need to use binary_crossentropy as a loss...
> Have you checked [tensorflow/tensorflow#48845](https://github.com/tensorflow/tensorflow/issues/48845)? This looks like a very likely root cause. @tanzhenyu can you confirm? If so, we should probably close this issue as it's a duplicate /...
@axelusarov is the slower prediction just for the first step (e.g. due to graph tracing), or is it also that every step is slower? I suppose that the single-class NMS...
Yeah this looks like there's some significant slowdown with the single-class NMS for TensorFlow, and it's probably just just due to graph tracing. This is something we should look into...
Renaming this issue to reflect that FasterRCNN needs to be ported.
given that YOLOV8 is available now, this is not high-value to add
Hey @chunxiangzheng -- where did we land on this PR? If you're interested in finishing it up, please feel free to address comments and re-request a review from Luke. I'm...
> all addressed @ianstenbit I think you moved the wrong guide to `examples`. It seems like you moved the original guide, not the one in this PR @LukeWood
These metrics are going to continue to be widely available in Keras Core moving forward, so I don't think there's a strong argument for having a second copy in KerasCV