jax.lax.conv_transpose#
- jax.lax.conv_transpose(lhs, rhs, strides, padding, rhs_dilation=None, dimension_numbers=None, transpose_kernel=False, precision=None, preferred_element_type=None)[source]#
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.
- Parameters:
lhs (Array) – a rank n+2 dimensional input array.
rhs (Array) – a rank n+2 dimensional array of kernel weights.
strides (Sequence[int]) – sequence of n integers, sets fractional stride.
padding (str | Sequence[tuple[int, 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.
rhs_dilation (Sequence[int] | None | None) – None, or a sequence of n integers, giving the dilation factor to apply in each spatial dimension of rhs. RHS dilation is also known as atrous convolution.
dimension_numbers (ConvGeneralDilatedDimensionNumbers | None) – tuple of dimension descriptors as in lax.conv_general_dilated. Defaults to tensorflow convention.
transpose_kernel (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.
precision (lax.PrecisionLike | None) – Optional. Either
None
, which means the default precision for the backend, aPrecision
enum value (Precision.DEFAULT
,Precision.HIGH
orPrecision.HIGHEST
) or a tuple of twoPrecision
enums indicating precision oflhs`
andrhs
.preferred_element_type (DTypeLike | None | None) – Optional. Either
None
, which means the default accumulation type for the input types, or a datatype, indicating to accumulate results to and return a result with that datatype.
- Returns:
Transposed N-d convolution, with output padding following the conventions of keras.layers.Conv2DTranspose.
- Return type: