max_pool3d#
- ivy.max_pool3d(x, kernel, strides, padding, /, *, data_format='NDHWC', out=None)[source]#
Compute a 3-D max pool given 5-D input x.
- Parameters:
x (
Union
[Array
,NativeArray
]) – Input volume [batch_size,d,h,w,d_in].kernel (
Union
[int
,Tuple
[int
],Tuple
[int
,int
,int
]]) – Convolution filters [d,h,w].strides (
Union
[int
,Tuple
[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'
)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:
- Returns:
ret – The result of the pooling 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 ofthe arguments.
Examples
>>> x = ivy.arange(48.).reshape((2, 3, 2, 2, 2)) >>> print(ivy.max_pool3d(x, 2, 2, 'VALID')) ivy.array([[[[[14., 15.]]]],
[[[[38., 39.]]]]])
>>> print(ivy.max_pool3d(x, 2, 2, 'SAME')) ivy.array([[[[[14., 15.]]],
[[[22., 23.]]]],
[[[[38., 39.]]],
[[[46., 47.]]]]])
- Array.max_pool3d(self, kernel, strides, padding, /, *, data_format='NDHWC', out=None)#
Compute a 3-D max pool given 5-D input x.
- Parameters:
self (
Array
) – Input volume [batch_size,d,h,w,d_in].kernel (
Union
[int
,Tuple
[int
],Tuple
[int
,int
,int
]]) – Convolution filters [d,h,w].strides (
Union
[int
,Tuple
[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'
)out (
Optional
[Array
]) – optional output array, for writing the result to. It must have (default:None
) a shape that the inputs broadcast to.
- Return type:
Array
- Returns:
ret – The result of the pooling operation.
Examples
>>> x = ivy.arange(48.).reshape((2, 3, 2, 2, 2)) >>> print(x.max_pool3d(2, 2, 'VALID')) ivy.array([[[[[14., 15.]]]], [[[[38., 39.]]]]]) >>> print(x.max_pool3d(2, 2, 'SAME')) ivy.array([[[[[14., 15.]]], [[[22., 23.]]]], [[[[38., 39.]]], [[[46., 47.]]]]])
- Container.max_pool3d(self, kernel, strides, padding, /, *, data_format='NDHWC', key_chains=None, to_apply=True, prune_unapplied=False, map_sequences=False, out=None)#
ivy.Container static method variant of ivy.max_pool3d. This method simply wraps the function, and so the docstring for ivy.max_pool3d also applies to this method with minimal changes.
- Parameters:
x – Input volume [batch_size,d,h,w,d_in].
kernel (
Union
[int
,Tuple
[int
],Tuple
[int
,int
,int
]]) – Convolution filters [d,h,w].strides (
Union
[int
,Tuple
[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'
)out (
Optional
[Container
]) – optional output array, for writing the result to. It must (default:None
) have a shape that the inputs broadcast to.
- Return type:
Container
- Returns:
ret – The result of the pooling operation.
Examples
>>> a = ivy.arange(12).reshape((1, 2, 1, 3, 2)) >>> b = ivy.arange(48).reshape((2, 2, 2, 3, 2)) >>> x = ivy.Container({'a': a, 'b': b}) >>> print(x.max_pool3d(2, 1, "VALID")) { a: ivy.array([], shape=(1, 1, 0, 2, 2)), b: ivy.array([[[[[20, 21], [22, 23]]]], [[[[44, 45], [46, 47]]]]]) }