Conv2d dimension orders of Tensorflow and iOS BNNS

conv2d

Tensorflow

x, y: [batch, height, width, depth]
core: [height, width, depth_in, depth_out]

iOS BNNS

x, y: [batch, depth, height, width]
core: [depth_out, depth_in, height, width]

1st full-conn after conv2d/pooling

Tensorflow

weights: [[height, width, depth].squeeze, size_y]

iOS

weights: [size_y, [depth, height, width].squeeze]