conv3d_transpose#

ivy.conv3d_transpose(x, filters, strides, padding, /, *, output_shape=None, filter_format='channel_last', data_format='NDHWC', dilations=1, bias=None, out=None)[source]#

Compute a 3-D transpose convolution given 5-D input x and filters arrays.

Parameters:
  • x (Union[Array, NativeArray]) – Input volume [batch_size,d,h,w,d_in] or [batch_size,d_in,d,h,w].

  • filters (Union[Array, NativeArray]) – Convolution filters [fd,fh,fw,d_out,d_in].

  • strides (Union[int, Tuple[int, 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]], default: None) – Shape of the output (Default value = None)

  • filter_format (str, default: 'channel_last') – Either “channel_first” or “channel_last”. “channel_first” corresponds to “IODHW”,input data formats, while “channel_last” corresponds to “DHWOI”.

  • data_format (str, default: 'NDHWC') – The ordering of the dimensions in the input, one of “NDHWC” or “NCDHW”. “NDHWC” corresponds to inputs with shape (batch_size, depth, height, width, channels), while “NCDHW” corresponds to input with shape (batch_size, channels, depth, height, width).

  • dilations (Union[int, Tuple[int, int, int]], default: 1) – The dilation factor for each dimension of input. (Default value = 1)

  • bias (Optional[Array], default: None) – Bias array of shape [d_out]

  • out (Optional[Array], default: None) – optional output array, for writing the result to. It must have a shape that the inputs broadcast to.

Return type:

Array

Returns:

ret – The result of the transpose convolution operation.

Examples

With ivy.Array input:

>>> x = ivy.random_normal(mean=0, std=1, shape=[1, 3, 28, 28, 3])
>>> filters = ivy.random_normal(mean=0, std=1, shape=[3, 3, 3, 6, 3])
>>> y = ivy.conv3d_transpose(x, filters, [2, 2, 2], 'SAME')
>>> print(y.shape)
ivy.Shape(1, 6, 56, 56, 6)
>>> x = ivy.random_normal(mean=0, std=1, shape=[1, 3, 64, 64, 3])
>>> filters = ivy.random_normal(mean=0, std=1, shape=[3, 3, 3, 6, 3])
>>> y = ivy.conv3d_transpose(x, filters, [2, 2, 2], 'VALID', dilations=[1, 1, 1])
>>> print(y.shape)
ivy.Shape(1, 7, 129, 129, 6)

With ivy.Container inputs:

>>> a = ivy.random_normal(mean=0, std=1, shape=[1, 3, 14, 14, 3])
>>> b = ivy.random_normal(mean=0, std=1, shape=[1, 3, 28, 28, 3])
>>> c = ivy.random_normal(mean=0, std=1, shape=[6, 3, 3, 3, 3])
>>> d = ivy.random_normal(mean=0, std=1, shape=[6, 3, 3, 3, 3])
>>> x = ivy.Container(a=a, b=b)
>>> filters = ivy.Container(c=c, d=d)
>>> y = ivy.conv3d_transpose(x, filters, [2, 2, 2], 'SAME')
>>> print(y.shape)
{
    a: {
        c: ivy.Shape(1, 6, 28, 28, 3),
        d: ivy.Shape(1, 6, 28, 28, 3)
    },
    b: {
        c: ivy.Shape(1, 6, 56, 56, 3),
        d: ivy.Shape(1, 6, 56, 56, 3)
    },
    c: {
        c: ivy.Shape(6, 6, 6, 6, 3),
        d: ivy.Shape(6, 6, 6, 6, 3)
    },
    d: {
        c: ivy.Shape(6, 6, 6, 6, 3),
        d: ivy.Shape(6, 6, 6, 6, 3)
    }
}

With a mix of ivy.Array and ivy.Container inputs:

>>> x = ivy.full((1, 6, 6, 6, 1), 2.7)
>>> a = ivy.random_normal(mean=0, std=1, shape=[3, 3, 3, 1, 1])
>>> b = ivy.random_normal(mean=0, std=1, shape=[3, 3, 3, 1, 1])
>>> filters = ivy.Container(a=a, b=b)
>>> y = ivy.conv3d_transpose(x, filters, [1, 1, 1], 'VALID', dilations=[1, 1, 1])
>>> print(y.shape)
{
    a: ivy.Shape(1, 8, 8, 8, 1),
    b: ivy.Shape(1, 8, 8, 8, 1)
}
>>> x = ivy.full((1, 6, 6, 6, 1), 1.23)
>>> a = ivy.array(ivy.random_normal(mean=0, std=1, shape=[3, 3, 3, 1, 1]))
>>> b = ivy.array(ivy.random_normal(mean=0, std=1, shape=[3, 3, 3, 1, 1]))
>>> filters = ivy.Container(a=a, b=b)
>>> y = ivy.conv3d_transpose(x, filters, [1, 1, 1], 'VALID', dilations=[1, 1, 1])
>>> print(y.shape)
{
    a: ivy.Shape(1, 8, 8, 8, 1),
    b: ivy.Shape(1, 8, 8, 8, 1)
}
Array.conv3d_transpose(self, filters, strides, padding, /, *, output_shape=None, filter_format='channel_last', data_format='NDHWC', dilations=1, bias=None, out=None)[source]#

ivy.Array instance method variant of ivy.conv3d_transpose. This method simply wraps the function, and so the docstring for ivy.conv3d_transpose also applies to this method with minimal changes.

Parameters:
  • self (Array) – Input volume [batch_size,d,h,w,d_in] or [batch_size,d_in,d,h,w].

  • filters (Union[Array, NativeArray]) – Convolution filters [fd,fh,fw,d_out,d_in].

  • strides (Union[int, Tuple[int], Tuple[int, int], Tuple[int, int, int]]) – The stride of the sliding window for each dimension of input.

  • padding (Union[str, List[int]]) – “SAME” or “VALID” indicating the algorithm, or list indicating the per-dimension paddings.

  • output_shape (Optional[Union[Shape, NativeShape]], default: None) – Shape of the output (Default value = None)

  • filter_format (str, default: 'channel_last') – Either “channel_first” or “channel_last”. “channel_first” corresponds to “IODHW”,input data formats, while “channel_last” corresponds to “DHWOI”.

  • data_format (str, default: 'NDHWC') –

    The ordering of the dimensions in the input, one of “NDHWC” or “NCDHW”. “NDHWC” corresponds to inputs with shape (batch_size,

    depth, height, width, channels), while “NCDHW” corresponds to input with shape (batch_size, channels, depth, height, width).

  • dilations (Union[int, Tuple[int], Tuple[int, int], Tuple[int, int, int]], default: 1) – The dilation factor for each dimension of input. (Default value = 1)

  • bias (Optional[Array], default: None) – Bias array of shape [d_out].

  • out (Optional[Array], default: None) – optional output array, for writing the result to. It must have a shape that 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, 3, 28, 28, 3])
>>> filters = ivy.random_normal(mean=0, std=1, shape=[3, 3, 3, 6, 3])
>>> y = x.conv3d_transpose(filters, 2, 'SAME')
>>> print(y.shape)
(1, 6, 56, 56, 6)
Container.conv3d_transpose(self, filters, strides, padding, /, *, output_shape=None, filter_format='channel_last', data_format='NDHWC', dilations=1, key_chains=None, to_apply=True, prune_unapplied=False, map_sequences=False, bias=None, out=None)[source]#

ivy.Container instance method variant of ivy.conv3d_transpose. This method simply wraps the function, and so the docstring for ivy.conv3d_transpose also applies to this method with minimal changes.

Parameters:
  • self (Container) – Input container with leaves of volume [batch_size,d,h,w,d_in] or [batch_size,d_in,d,h,w].

  • filters (Union[Array, NativeArray, Container]) – Convolution filters [fd,fh,fw,d_out,d_in].

  • strides (Union[int, Tuple[int], Tuple[int, int], Tuple[int, int, int], Container]) – The stride of the sliding window for each dimension of input.

  • padding (Union[str, List[int], Container]) – “SAME” or “VALID” indicating the algorithm, or list indicating the per-dimension paddings.

  • output_shape (Optional[Union[Array, NativeArray, Container]], default: None) – Shape of the output (Default value = None)

  • filter_format (str, default: 'channel_last') – Either “channel_first” or “channel_last”. “channel_first” corresponds to “IODHW”,input data formats, while “channel_last” corresponds to “DHWOI”.

  • data_format (str, default: 'NDHWC') –

    The ordering of the dimensions in the input, one of “NDHWC” or “NCDHW”. “NDHWC” corresponds to inputs with shape (batch_size,

    depth, height, width, channels), while “NCDHW” corresponds to input with shape (batch_size, channels, depth, height, width).

  • dilations (Union[int, Tuple[int], Tuple[int, int], Tuple[int, int, int]], default: 1) – The dilation factor for each dimension of input. (Default value = 1)

  • bias (Optional[Container], default: None) – Bias array of shape [d_out].

  • out (Optional[Container], default: None) – optional output container, for writing the result to. It must have a shape that the inputs broadcast to.

Return type:

Container

Returns:

ret – The result of the transpose convolution operation in a container.

Examples

>>> x = ivy.Container(a = ivy.ones((1, 3, 3, 3, 1)).astype(ivy.float32) )
>>> filters = ivy.ones((3, 3, 3, 1, 1)).astype(ivy.float32)
>>> result = x.conv3d(filters, 2, 'SAME')
>>> print(result)
{
    a: ivy.array([[[[[8.],
                     [8.]],
                    [[8.],
                     [8.]]],
                  [[[8.],
                     [8.]],
                    [[8.],
                     [8.]]]]])
}