Aditya Kane
Aditya Kane
@fchollet @qlzh727 I was trying to resolve [#425 of keras-cv](https://github.com/keras-team/keras-cv/issues/425) by simply adding a single Identity layer in the `layers` list in case it was empty or None. However, there...
@LukeWood @sayakpaul Corrected RegNets implementation which was causing tests to fail: - Added input_tensor argument. - `num_classes` -> `classes`
@sayakpaul @LukeWood @ianjjohnson Ported over EfficientNets (V1 and V2) from keras. Made changes wherever necessary to stick to the KerasCV code style. /auto Closes #551
@sayakpaul @LukeWood @ianjjohnson Dataset loading and preprocessing in vision is generally a messy ordeal and the additional boilerplate code for TFRecords makes it worse. A probable solution for this can...
@sayakpaul @LukeWood I'm interested in porting [RegNets](https://github.com/keras-team/keras/blob/master/keras/applications/regnet.py) from keras to keras_cv.
@cgarciae Great work with the library! Love it! Found a minor nit in the README so reporting it.
Current implementation of RandomResizedCrop (#738) does not have bounding box support. Need to add bounding box support while taking special care of fill_mode="reflect". /cc @LukeWood
@sayakpaul @LukeWood Added RegNets to keras_cv as per discussions in #679, #530 , #552 , #590 /auto Closes #530
@haifeng-jin @fchollet This issue is both a bug report and a feature request. https://github.com/tensorflow/tensorflow/issues/48531 shows an issue of KerasTensor. Of course, the [docstring](https://github.com/keras-team/keras/blob/master/keras/engine/keras_tensor.py#L32-L111) elaborates it even further. IMO, given the...
Fixed a typo in `modeling_clip.py`.