MXNET symbolic implementation of - 'An intriguing failing of convolutional neural networks and the CoordConv solution' (arxiv.org/abs/1807.03247)
usage:
- download the .py file
- from CoordConv_sym import CoordConv2D
- in your model, replace mx.sym.Convolution() with CoordConv2D()
- train model as usual
initially supports 2d-conv only, you may modify it for your own purposes