Wrong denominators when normalize xx_channel and yy_channel?

[jiayily]

Hi, in your code you normalize xx_channel and yy_channel as following: https://github.com/uber-research/CoordConv/blob/27fab8b86efac87c262c7c596a0c384b83c9d806/CoordConv.py#L70 https://github.com/uber-research/CoordConv/blob/27fab8b86efac87c262c7c596a0c384b83c9d806/CoordConv.py#L71 I think it should be: xx_channel = tf.cast(xx_channel, 'float32') / (self.y_dim - 1) yy_channel = tf.cast(yy_channel, 'float32') / (self.x_dim - 1) That is the denominators are wrong?

[jeanibarz]

Yes it is, there are already 2 pull requests for that issue (one created since 2020). I think that the repository is not maintained anymore.