Aditya Kane
                                            Aditya Kane
                                        
                                    @LukeWood I'm interested to do this.
Yup, on it.
@LukeWood do we assume the bounding boxes to be of a specific type? Like `xyxy` or `rel_xyxy`?
@sayakpaul @LukeWood I'm interested to work on this.
@LukeWood My understanding is as follows: - Assume an input image of 300x400. (height x width) - First we sample a zoom factor (would be
Okay. Zoom factor is almost clear to me now. Assuming we use a zoom factor of 0.5 (which will zoom out the image) we get a 600x800 image, right? How...
@LukeWood Thanks for this, it really helps! I have two concerns regarding this approach: 1. I understand that this is quite close to the current implementation, in terms of the...
@LukeWood Yup, got it. I'll create a PR for this over the weekend.
@martin-gorner @LukeWood @sayakpaul > An edge case not yet considered is what happens when the computed crop_size ends up being larger, in at least one dimension, than the image. To...
@martin-gorner Understood. @LukeWood @sayakpaul I guess I will rewrite the implementation and drop `tf.image.crop_and_resize` as it does not have this functionality.