conv2d_transpose#

ivy.conv2d_transpose(x, filters, strides, padding, /, *, output_shape=None, data_format='NHWC', dilations=1, out=None)[source]#

Compute a 2-D transpose convolution given 4-D input x and filters arrays.

Parameters:

x (Union[Array, NativeArray]) – Input image [batch_size,h,w,d_in] or [batch_size,d_in,h,w].
filters (Union[Array, NativeArray]) – Convolution filters [fh,fw,d_in,d_out].
strides (Union[int, Tuple[int, int]]) – The stride of the sliding window for each dimension of input.
padding (str) – Either ‘SAME’ (padding so that the output’s shape is the same as the input’s), or ‘VALID’ (padding so that the output’s shape is output_shape).
output_shape (Optional[Union[Shape, NativeShape]]) – Shape of the output (Default value = None) (default: None)
data_format (str) – The ordering of the dimensions in the input, one of “NHWC” or “NCHW”. “NHWC” (default: 'NHWC') corresponds to inputs with shape (batch_size, height, width, channels), while “NCHW” corresponds to input with shape (batch_size, channels, height, width).
dilations (Union[int, Tuple[int, int]]) – The dilation factor for each dimension of input. (Default value = 1) (default: 1)
out (Optional[Array]) – optional output array, for writing the result to. It must have a shape that the (default: None) inputs broadcast to.

Return type:

Array

Returns:

ret – The result of the transpose convolution operation.
Both the description and the type hints above assumes an array input for simplicity,
but this function is nestable, and therefore also accepts ivy.Container
instances in place of any of the arguments.

Examples

With ivy.Array input: >>> x = ivy.random_normal(mean=0, std=1, shape=[1, 28, 28, 3]) >>> filters = ivy.random_normal(mean=0, std=1, shape=[3, 3, 3, 6]) >>> y = ivy.conv2d_transpose(x, filters, 2, ‘SAME’) >>> print(y.shape) (1, 56, 56, 6)

>>> x = ivy.random_normal(mean=0, std=1, shape=[1, 128, 128, 64])
>>> filters = ivy.random_normal(mean=0, std=1, shape=[1, 1, 64, 64])
>>> ivy.conv2d_transpose(x, filters, 1, 'VALID', out=x)
>>> print(x.shape)
(1, 128, 128, 64)

>>> x = ivy.random_normal(mean=0, std=1, shape=[1, 256, 256, 64])
>>> y = ivy.zeros_like(x)
>>> filters = ivy.random_normal(mean=0, std=1, shape=[3, 3, 64, 32])
>>> ivy.conv2d_transpose(x, filters, [1, 1, 1], 'VALID', out=y)
>>> print(y.shape)
(1, 258, 258, 32)

With one ivy.Container inputs: >>> x = ivy.full((1, 6, 6, 1), 2.7) >>> a = ivy.random_normal(mean=0, std=1, shape=[3, 3, 1, 1]) >>> b = ivy.random_normal(mean=0, std=1, shape=[3, 3, 1, 1]) >>> filters = ivy.Container(a=a, b=b) >>> y = ivy.conv2d_transpose(x, filters, 1, ‘VALID’, dilations=2) >>> print(y.shape) {

a: [1,10,10,1], b: [1,10,10,1]

}

With multiple ivy.Container inputs: >>> a = ivy.random_normal(mean=0, std=1, shape=[1, 14, 14, 3]) >>> b = ivy.random_normal(mean=0, std=1, shape=[1, 28, 28, 3]) >>> c = ivy.random_normal(mean=0, std=1, shape=[3, 3, 3, 6]) >>> d = ivy.random_normal(mean=0, std=1, shape=[3, 3, 3, 6]) >>> x = ivy.Container(a=a, b=b) >>> filters = ivy.Container(c=c, d=d) >>> y = ivy.conv2d_transpose(x, filters, 2, ‘SAME’) >>> print(y.shape) {

a: {
c: [1,28,28,6], d: [1,28,28,6]

}, b: {

c: [1,56,56,6], d: [1,56,56,6]

}

}

Array.conv2d_transpose(self, filters, strides, padding, /, *, output_shape=None, data_format='NHWC', dilations=1, out=None)#

ivy.Array instance method variant of ivy.conv2d_transpose. This method simply wraps the function, and so the docstring for ivy.conv2d_transpose also applies to this method with minimal changes.

Parameters:

self (Array) – Input image [batch_size,h,w,d_in] or [batch_size,d_in,h,w].
filters (Union[Array, NativeArray]) – Convolution filters [fh,fw,d_in,d_out].
strides (Union[int, Tuple[int, int]]) – The stride of the sliding window for each dimension of input.
padding (str) – “SAME” or “VALID” indicating the algorithm, or list indicating the per-dimension paddings.
output_shape (Optional[Union[Shape, NativeShape]]) – Shape of the output (Default value = None) (default: None)
data_format (str) – The ordering of the dimensions in the input, one of “NHWC” or “NCHW”. “NHWC” (default: 'NHWC') corresponds to inputs with shape (batch_size, height, width, channels), while “NCHW” corresponds to input with shape (batch_size, channels, height, width). Default is "NHWC".
dilations (Union[int, Tuple[int, int]]) – The dilation factor for each dimension of input. (Default value = 1) (default: 1)
out (Optional[Array]) – Optional output array, for writing the result to. It must have a shape that (default: None) the inputs broadcast to.

Return type:

Array

Returns:

ret – The result of the transpose convolution operation.

Examples

>>> x = ivy.random_normal(mean=0, std=1, shape=[1, 28, 28, 3])
>>> filters = ivy.random_normal(mean=0, std=1, shape=[3, 3, 3, 6])
>>> y = x.conv2d_transpose(filters, 2, 'SAME')
>>> print(y.shape)
(1, 56, 56, 6)

Container.conv2d_transpose(self, filters, strides, padding, /, *, output_shape=None, data_format='NHWC', dilations=1, key_chains=None, to_apply=True, prune_unapplied=False, map_sequences=False, out=None)#

ivy.Container instance method variant of ivy.conv2d_transpose. This method simply wraps the function, and so the docstring for ivy.conv2d also applies to this method with minimal changes.

Parameters:

self (Container) – Input image [batch_size,h,w,d_in].
filters (Union[Array, NativeArray, Container]) – Convolution filters [fh,fw,d_in,d_out].
strides (Union[int, Tuple[int, int]]) – The stride of the sliding window for each dimension of input.
padding (str) – “SAME” or “VALID” indicating the algorithm, or list indicating the per-dimension paddings.
output_shape (Optional[Union[Array, NativeArray, Container]]) – Shape of the output (Default value = None) (default: None)
data_format (str) – “NHWC” or “NCHW”. Defaults to “NHWC”. (default: 'NHWC')
dilations (Union[int, Tuple[int, int]]) – The dilation factor for each dimension of input. (Default value = 1) (default: 1)
key_chains (Optional[Union[List[str], Dict[str, str]]]) – The key-chains to apply or not apply the method to. Default is None. (default: None)
to_apply (bool) – If True, the method will be applied to key_chains, otherwise key_chains (default: True) will be skipped. Default is True.
prune_unapplied (bool) – Whether to prune key_chains for which the function was not applied. (default: False) Default is False.
map_sequences (bool) – Whether to also map method to sequences (lists, tuples). (default: False) Default is False.
out (Optional[Container]) – optional output array, for writing the result to. It must have a shape (default: None) that the inputs broadcast to.

Return type:

Container

Returns:

ret – The result of the convolution operation.

Examples

>>> a = ivy.random_normal(mean=0, std=1, shape=[1, 14, 14, 3])
>>> b = ivy.random_normal(mean=0, std=1, shape=[1, 28, 28, 3])
>>> c = ivy.random_normal(mean=0, std=1, shape=[3, 3, 3, 6])
>>> d = ivy.random_normal(mean=0, std=1, shape=[3, 3, 3, 6])
>>> x = ivy.Container(a=a, b=b)
>>> filters = ivy.Container(c=c, d=d)
>>> y = x.conv2d_transpose(x, filters, 2, 'SAME')
>>> print(y.shape)
{
    a: {
        c: [1,28,28,6],
        d: [1,28,28,6]
    },
    b: {
        c: [1,56,56,6],
        d: [1,56,56,6]
    }
}