conv3d#

ivy.conv3d(x, filters, strides, padding, /, *, data_format='NDHWC', dilations=1, out=None)[source]#

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

Parameters:

x (Union[Array, NativeArray, Container]) – Input 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_in,d_out].
strides (Union[int, Tuple[int, int, int]]) – The stride of the sliding window for each dimension of input.
padding (Union[str, int, Sequence[Tuple[int, int]]]) – either the string ‘SAME’ (padding with zeros evenly), the string ‘VALID’ (no padding), or a sequence of n (low, high) integer pairs that give the padding to apply before and after each spatial dimension.
data_format (str) – The ordering of the dimensions in the input, one of “NDHWC” or “NCDHW”. “NDHWC” (default: '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]]) – 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 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.array               ([[[1., 2. ,1.], [1., 2. ,1.], [1., 2. ,1.]],                [[1., 2. ,1.], [1., 2. ,1.], [1., 2. ,1.]],                [[1., 2. ,1.], [1., 2. ,1.], [1., 2. ,1.]]]).reshape((1, 3, 3, 3, 1))

>>> filters = ivy.array([[[0.,1.,0.],                              [0.,1.,0.],                              [0.,1.,0.]]]).reshape((1,3,3,1,1))

>>> result = ivy.conv3d(x, filters, (1,1,1), 'SAME', data_format = 'NDHWC',                            dilations = (1,1,1))

>>> print(result)
ivy.array([[[[[2.],[4.],[2.]],[[3.],[6.],[3.]],[[2.],[4.],[2.]]],
            [[[2.],[4.],[2.]],[[3.],[6.],[3.]],[[2.],[4.],[2.]]],
            [[[2.],[4.],[2.]],[[3.],[6.],[3.]],[[2.],[4.],[2.]]]]])

With one ivy.Container input:

>>> 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 = ivy.conv3d(x, filters, 2, 'SAME')
>>> print(result)
{
    a: ivy.array([[[[[8.],[8.]],[[8.],[8.]]],[[[8.],[8.]],[[8.],[8.]]]]])
}

With multiple ivy.Container input:

>>> x = ivy.Container( a = ivy.random_normal(mean = 0, std = 1,                               shape = [1, 3, 5, 5, 1]),                           b = ivy.random_normal(mean = 0, std = 1,                               shape = [1, 5, 32 ,32, 3]),                           c = ivy.random_normal(mean = 0, std = 1,                               shape = [1, 32, 32, 32, 1]))

>>> filters = ivy.ones((3, 5, 5, 1, 3)).astype(ivy.float32) #DHWIO

>>> result = ivy.conv3d(x, filters, 1, 'SAME')
>>> print(result.cont_shapes)
{
    a: [1,3,5,5,3],
    b: [1,5,32,32,3],
    c: [1,32,32,32,3]
}

Array.conv3d(self, filters, strides, padding, /, *, data_format='NDHWC', dilations=1, out=None)#

ivy.Array instance method variant of ivy.conv3d. This method simply wraps the function, and so the docstring for ivy.conv3d also applies to this method with minimal changes.

Parameters:

x – Input volume [batch_size,d,h,w,d_in].
filters (Union[Array, NativeArray]) – Convolution filters [fd,fh,fw,d_in,d_out].
strides (Union[int, Tuple[int, 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.
data_format (str) – “NDHWC” or “NCDHW”. Defaults to “NDHWC”. (default: 'NDHWC')
dilations (Union[int, Tuple[int, 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 convolution operation.

Examples

>>> x = ivy.ones((1, 3, 3, 3, 1)).astype(ivy.float32)

>>> filters = ivy.ones((1, 3, 3, 1, 1)).astype(ivy.float32)

>>> result = x.conv3d(filters, 2, 'SAME')
>>> print(result)
ivy.array([[[[[4.],[4.]],[[4.],[4.]]],[[[4.],[4.]],[[4.],[4.]]]]])

Container.conv3d(self, filters, strides, padding, /, *, data_format='NDHWC', dilations=1, key_chains=None, to_apply=True, prune_unapplied=False, map_sequences=False, out=None)#

ivy.Container instance method variant of ivy.conv3d. This method simply wraps the function, and so the docstring for ivy.conv3d also applies to this method with minimal changes.

Parameters:

x – Input volume [batch_size,d,h,w,d_in].
filters (Union[Array, NativeArray, Container]) – Convolution filters [fdfh,fw,d_in,d_out].
strides (Union[int, Tuple[int, 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.
data_format (str) – “NDHWC” or “NCDHW”. Defaults to “NDHWC”. (default: 'NDHWC')
dilations (Union[int, Tuple[int, int, int]]) – The dilation factor for each dimension of input. (Default value = 1) (default: 1)
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

>>> x = ivy.Container(a = ivy.full((1, 2, 3, 3, 1),0.5),                              b = ivy.full((1, 2, 5, 5, 1),1.))

>>> filters = ivy.ones((3, 3, 3, 1, 1))

>>> result = x.conv3d(filters, 2, 'SAME')
>>> print(result)
{
    a: ivy.array([[[[[4.],[4.]],[[4.],[4.]]]]]),
    b: ivy.array([[[[[8.],[12.],[8.]],[[12.],[18.],[12.]],[[8.],[12.],[8.]]]]])
}