conv_transpose(lhs, rhs, strides, padding, rhs_dilation=None, dimension_numbers=None, transpose_kernel=False, precision=None)¶
Convenience wrapper for calculating the N-d convolution “transpose”.
This function directly calculates a fractionally strided conv rather than indirectly calculating the gradient (transpose) of a forward convolution.
Any) – a rank n+2 dimensional input array.
Any) – a rank n+2 dimensional array of kernel weights.
int]]]) – ‘SAME’, ‘VALID’ will set as transpose of corresponding forward conv, or a sequence of n integer 2-tuples describing before-and-after padding for each n spatial dimension.
bool) – if True flips spatial axes and swaps the input/output channel axes of the kernel. This makes the output of this function identical to the gradient-derived functions like keras.layers.Conv2DTranspose applied to the same kernel. For typical use in neural nets this is completely pointless and just makes input/output channel specification confusing.
- Return type
Transposed N-d convolution, with output padding following the conventions of keras.layers.Conv2DTranspose.