forked from mindspore-Ecosystem/mindspore
modify maxpool3d errors
This commit is contained in:
parent
8d04817a64
commit
8188357ab0
|
|
@ -18,9 +18,9 @@ mindspore.nn.AvgPool3d
|
|||
\text{input}(N_i, C_j, s_0 \times d + l, s_1 \times h + m, s_2 \times w + n)
|
||||
|
||||
参数：
|
||||
- **kernel_size** (Union[int, tuple[int]]) - 指定池化核尺寸大小。如果为int，则同时代表池化核的深度，高度和宽度。如果为tuple，其值必须包含三个int，分别表示池化核的深度，高度和宽度。
|
||||
- **stride** (Union[int, tuple[int]]) - 池化操作的移动步长。如果为int，则同时代表池化核的深度，高度和宽度方向上的移动步长。如果为tuple，其值必须包含三个整数值，分别表示池化核的深度，高度和宽度方向上的移动步长。默认值：None。
|
||||
- **padding** (Union(int, tuple[int])) - 需要填充的pad值，默认值：0。如果 `padding` 为整数，则分别在头，尾，上，下，左，右都填充padding，如果 `padding` 是一个六个整数的元组，则分别在头，尾，上，下，左，右填充padding[0]，padding[1]，padding[2]，padding[3]，padding[4]，padding[5]。
|
||||
- **kernel_size** (Union[int, tuple[int]]) - 指定池化核尺寸大小。如果为int，则同时代表池化核的深度，高度和宽度。如果为tuple，其值必须包含三个int，分别表示池化核的深度，高度和宽度。取值必须为正整数。
|
||||
- **stride** (Union[int, tuple[int]]) - 池化操作的移动步长。如果为int，则同时代表池化核的深度，高度和宽度方向上的移动步长。如果为tuple，其值必须包含三个整数值，分别表示池化核的深度，高度和宽度方向上的移动步长。取值必须为正整数。如果值为None，则使用默认值 `kernel_size`。
|
||||
- **padding** (Union(int, tuple[int])) - 需要填充的pad值，默认值：0。取值不能为负数。如果 `padding` 为整数，则分别在头，尾，上，下，左，右都填充padding，如果 `padding` 是一个六个整数的元组，则分别在头，尾，上，下，左，右填充padding[0]，padding[1]，padding[2]，padding[3]，padding[4]，padding[5]。
|
||||
- **ceil_mode** (bool) - 若为True，使用ceil来计算输出shape。若为False，使用floor来计算输出shape。默认值：False。
|
||||
- **count_include_pad** (bool) - 平均计算是否包括零填充。默认值：True。
|
||||
- **divisor_override** (int) - 如果被指定为非0参数，该参数将会在平均计算中被用作除数，否则将会使用 `kernel_size` 作为除数，默认值：None。
|
||||
|
|
|
|||
|
|
@ -15,12 +15,12 @@ mindspore.nn.MaxPool3d
|
|||
\text{input}(N_i, C_j, s_0 \times d + l, s_1 \times h + m, s_2 \times w + n)
|
||||
|
||||
参数：
|
||||
- **kernel_size** (Union[int, tuple[int]]) - 指定池化核尺寸大小，如果为整数，则代表池化核的深度，高和宽。如果为tuple，其值必须包含三个整数值分别表示池化核的深度，高和宽。默认值：1。
|
||||
- **stride** (Union[int, tuple[int]]) - 池化操作的移动步长，如果为整数，则代表池化核的深度，高和宽方向的移动步长。如果为tuple，其值必须包含三个整数值分别表示池化核的深度，高和宽的移动步长。默认值：1。
|
||||
- **padding** (Union[int, tuple[int]]) - 池化填充长度。可以是一个整数表示在深度，高度和宽度方向的填充长度，或者包含三个整数的tuple，分别表示在深度，高度和宽度方向的填充长度。
|
||||
- **kernel_size** (Union[int, tuple[int]]) - 指定池化核尺寸大小，如果为int，则代表池化核的深度，高和宽。如果为tuple，其值必须包含三个正整数值分别表示池化核的深度，高和宽。取值必须为正整数。
|
||||
- **stride** (Union[int, tuple[int]]) - 池化操作的移动步长，如果为int，则代表池化核的深度，高和宽方向的移动步长。如果为tuple，其值必须包含三个正整数值分别表示池化核的深度，高和宽的移动步长。取值必须为正整数。如果值为None，则使用默认值 `kernel_size`。
|
||||
- **padding** (Union[int, tuple[int]]) - 池化填充长度。可以是一个整数表示在深度，高度和宽度方向的填充长度，或者包含三个整数的tuple，分别表示在深度，高度和宽度方向的填充长度。取值不能为负数。默认值：0。
|
||||
- **dilation** (Union[int, tuple[int]]) - 控制池化核内元素的间距。默认值：1。
|
||||
- **return_indices** (bool) - 若为True，则返回一个包含两个Tensor的Tuple，表示池化的计算结果以及生成max值的位置，否则，仅返回池化计算结果。
|
||||
- **ceil_mode** (bool) - 若为True，使用ceil来计算输出shape。若为False，使用floor来计算输出shape。默认值：False。
|
||||
- **return_indices** (bool) - 若为True，则返回一个包含两个Tensor的Tuple，表示池化的计算结果以及生成max值的位置，否则，仅返回池化计算结果。默认值：False。
|
||||
- **ceil_mode** (bool) - 若为True，使用ceil模式来计算输出shape。若为False，使用floor模式来计算输出shape。默认值：False。
|
||||
|
||||
输入：
|
||||
- **x** (Tensor) - shape为 :math:`(N_{in}, C_{in}, D_{in}, H_{in}, W_{in})` 或者 :math:`(C_{in}, D_{in}, H_{in}, W_{in})` 的Tensor。数据类型必须为int8、 int16、 int32、 int64、 uint8、 uint16、 uint32、 uint64、 float16、 float32 或者 float64。
|
||||
|
|
|
|||
|
|
@ -249,16 +249,18 @@ class MaxPool3d(Cell):
|
|||
Args:
|
||||
kernel_size (Union[int, tuple[int]]): The size of kernel used to take the maximum value,
|
||||
is an int number that represents depth, height and width of the kernel, or a tuple
|
||||
of three int numbers that represent depth, height and width respectively. Default: 1.
|
||||
of three int numbers that represent depth, height and width respectively.
|
||||
The value must be a positive integer.
|
||||
stride (Union[int, tuple[int]]): The moving stride of pooling operation, an int number that represents
|
||||
the moving stride of pooling kernel in the directions of depth, height and the width,
|
||||
or a tuple of three int numbers that represent depth, height and width of movement respectively. Default: 1.
|
||||
or a tuple of three int numbers that represent depth, height and width of movement respectively.
|
||||
The value must be a positive integer. If the value is None, the default value `kernel_size` is used.
|
||||
padding (Union[int, tuple[int]]): Pooling padding length. An int number that represents the depth,
|
||||
height and width of movement are both stride, or a tuple of three int numbers that represent depth,
|
||||
height and width of movement respectively.
|
||||
height and width of movement respectively. The value cannot be negative. Default: 0.
|
||||
dilation (Union[int, tuple[int]]): Control the spacing of elements in the pooling kernel. Default: 1.
|
||||
return_indices (bool): If True, output is a Tuple of 2 Tensors, representing the maxpool result and where
|
||||
the max values are generated. Otherwise, only the maxpool result is returned.
|
||||
the max values are generated. Otherwise, only the maxpool result is returned. Default: False.
|
||||
ceil_mode (bool): Whether to use ceil or floor to calculate output shape. Default: False.
|
||||
|
||||
Inputs:
|
||||
|
|
@ -328,6 +330,7 @@ class MaxPool3d(Cell):
|
|||
def __init__(self, kernel_size, stride=None, padding=0, dilation=1, return_indices=False, ceil_mode=False):
|
||||
"""Initialize MaxPool3d."""
|
||||
super(MaxPool3d, self).__init__()
|
||||
stride = stride if (stride is not None) else kernel_size
|
||||
self.return_indices = return_indices
|
||||
self.max_pool = MaxPool3DWithArgmax(kernel_size, stride, padding, dilation, ceil_mode)
|
||||
self.expand_dims = P.ExpandDims()
|
||||
|
|
@ -523,13 +526,16 @@ class AvgPool3d(Cell):
|
|||
kernel_size (Union[int, tuple[int]]): The size of kernel used to take the average value,
|
||||
is an int number that represents depth, height and width are both kernel_size, or a tuple
|
||||
of three int numbers that represent depth, height and width respectively.
|
||||
The value must be a positive integer.
|
||||
stride (Union[int, tuple[int]]): The distance of kernel moving, an int number that represents
|
||||
the depth, height and width of movement are both stride, or a tuple of three int numbers that
|
||||
represent depth, height and width of movement respectively. Default: None.
|
||||
padding (Union(int, tuple[int])): The padding value to be filled. Default: 0. If `padding` is an integer,
|
||||
the paddings of head, tail, top, bottom, left and right are the same, equal to padding.
|
||||
If `padding` is a tuple of six integers, the padding of head, tail, top, bottom, left and right
|
||||
equal to padding[0], padding[1], padding[2], padding[3], padding[4] and padding[5] correspondingly.
|
||||
represent depth, height and width of movement respectively. The value must be a positive integer.
|
||||
If the value is None, the default value `kernel_size` is used.
|
||||
padding (Union(int, tuple[int])): The padding value to be filled. Default: 0. The value cannot be negative.
|
||||
If `padding` is an integer, the paddings of head, tail, top, bottom, left and right are the same,
|
||||
equal to padding.
|
||||
If `padding` is a tuple of six integers, the padding of head, tail, top, bottom, left and right
|
||||
equal to padding[0], padding[1], padding[2], padding[3], padding[4] and padding[5] correspondingly.
|
||||
ceil_mode (bool): If True, use ceil to compute the output shape instead of floor. Default: False.
|
||||
count_include_pad (bool): If True, averaging calculation will include the zero-padding. Default: True.
|
||||
divisor_override (int): If specified, it will be used as divisor in the averaging calculation,
|
||||
|
|
|
|||
Loading…
Reference in New Issue