p47068915
/
mindspore
forked from mindspore-Ecosystem/mindspore
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

!5702 API comment for operations part1 

Merge pull request !5702 from Simson/enhancement-API
This commit is contained in:
mindspore-ci-bot 2020-09-03 19:58:14 +08:00 committed by Gitee
parent 01da7d2c1a 76bbfdea75
commit a9f4a24e2a
10 changed files with 210 additions and 196 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
mindspore/nn/graph_kernels/graph_kernels.py
View File

@ -33,7 +33,7 @@ class InplaceAssign(PrimitiveWithInfer):
Inputs:
- **variable** (Parameter) - The `Parameter`.
- **value** (Tensor) - The value to assign.
- **value** (Tensor) - The value to be assigned.
- **depend** (Tensor) - The dependent tensor to keep this op connected in graph.
Outputs:
@ -274,7 +274,7 @@ class EqualCount(GraphKernel):
"""
Computes the number of the same elements of two tensors.
The two input tensors should have same shape and data type.
The two input tensors should have the same shape and data type.
Inputs:
x (Tensor): the first input tensor.
@ -1139,9 +1139,9 @@ class LambNextMV(GraphKernel):
Outputs:
Tuple of 2 Tensor.
- **add3** (Tensor) - The shape is the same as the shape after broadcasting, and the data type is
- **add3** (Tensor) - the shape is the same as the one after broadcasting, and the data type is
the one with high precision or high digits among the inputs.
- **realdiv4** (Tensor) - The shape is the same as the shape after broadcasting, and the data type is
- **realdiv4** (Tensor) - the shape is the same as the one after broadcasting, and the data type is
the one with high precision or high digits among the inputs.
Examples:

2
mindspore/nn/optim/adam.py
View File

@ -194,7 +194,7 @@ class Adam(Optimizer):
Default: 0.999.
eps (float): Term added to the denominator to improve numerical stability. Should be greater than 0. Default:
1e-8.
use_locking (bool): Whether to enable a lock to protect updating variable tensors.
use_locking (bool): Whether to enable a lock to protect variable tensors from being updated.
If true, updates of the var, m, and v tensors will be protected by a lock.
If false, the result is unpredictable. Default: False.
use_nesterov (bool): Whether to use Nesterov Accelerated Gradient (NAG) algorithm to update the gradients.

2
mindspore/nn/optim/lazyadam.py
View File

@ -141,7 +141,7 @@ class LazyAdam(Optimizer):
Default: 0.999.
eps (float): Term added to the denominator to improve numerical stability. Should be greater than 0. Default:
1e-8.
use_locking (bool): Whether to enable a lock to protect updating variable tensors.
use_locking (bool): Whether to enable a lock to protect variable tensors from being updated.
If true, updates of the var, m, and v tensors will be protected by a lock.
If false, the result is unpredictable. Default: False.
use_nesterov (bool): Whether to use Nesterov Accelerated Gradient (NAG) algorithm to update the gradients.

2
mindspore/nn/optim/rmsprop.py
View File

@ -80,7 +80,7 @@ class RMSProp(Optimizer):
.. math::
w = w - m_{t}
where, :math:`w` represents `params`, which will be updated.
where :math:`w` represents `params`, which will be updated.
:math:`g_{t}` is mean gradients, :math:`g_{t-1}` is the last moment of :math:`g_{t}`.
:math:`s_{t}` is the mean square gradients, :math:`s_{t-1}` is the last moment of :math:`s_{t}`,
:math:`m_{t}` is moment, the delta of `w`, :math:`m_{t-1}` is the last moment of :math:`m_{t}`.

2
mindspore/ops/operations/__init__.py
View File

@ -16,7 +16,7 @@
"""
Primitive operator classes.
A collection of operators to build nerual networks or computing functions.
A collection of operators to build neural networks or to compute functions.
"""
from .image_ops import (CropAndResize)

78
mindspore/ops/operations/array_ops.py
View File

@ -222,11 +222,11 @@ class Cast(PrimitiveWithInfer):
Inputs:
- **input_x** (Union[Tensor, Number]) - The shape of tensor is :math:`(x_1, x_2, ..., x_R)`.
The tensor to be casted.
The tensor to be cast.
- **type** (dtype.Number) - The valid data type of the output tensor. Only constant value is allowed.
Outputs:
Tensor, the shape of tensor is :math:`(x_1, x_2, ..., x_R)`, same as `input_x`.
Tensor, the shape of tensor is the same as `input_x`, :math:`(x_1, x_2, ..., x_R)`.
Examples:
>>> input_np = np.random.randn(2, 3, 4, 5).astype(np.float32)
@ -983,7 +983,7 @@ class TupleToArray(PrimitiveWithInfer):
- **input_x** (tuple) - A tuple of numbers. These numbers have the same type. Only constant value is allowed.
Outputs:
Tensor, if the input tuple contain `N` numbers, then the output tensor shape is (N,).
Tensor, if the input tuple contain `N` numbers, then the shape of the output tensor is (N,).
Examples:
>>> type = P.TupleToArray()((1,2,3))
@ -1148,11 +1148,11 @@ class Argmax(PrimitiveWithInfer):
"""
Returns the indices of the max value of a tensor across the axis.
If the shape of input tensor is :math:`(x_1, ..., x_N)`, the output tensor shape is
If the shape of input tensor is :math:`(x_1, ..., x_N)`, the shape of the output tensor will be
:math:`(x_1, ..., x_{axis-1}, x_{axis+1}, ..., x_N)`.
Args:
axis (int): Axis on which Argmax operation applies. Default: -1.
axis (int): Axis where the Argmax operation applies to. Default: -1.
output_type (:class:`mindspore.dtype`): An optional data type of `mindspore.dtype.int32`.
Default: `mindspore.dtype.int32`.
@ -1195,11 +1195,11 @@ class Argmin(PrimitiveWithInfer):
"""
Returns the indices of the min value of a tensor across the axis.
If the shape of input tensor is :math:`(x_1, ..., x_N)`, the output tensor shape is
If the shape of input tensor is :math:`(x_1, ..., x_N)`, the shape of the output tensor is
:math:`(x_1, ..., x_{axis-1}, x_{axis+1}, ..., x_N)`.
Args:
axis (int): Axis on which Argmin operation applies. Default: -1.
axis (int): Axis where the Argmin operation applies to. Default: -1.
output_type (:class:`mindspore.dtype`): An optional data type of `mindspore.dtype.int32`.
Default: `mindspore.dtype.int32`.
@ -1241,16 +1241,17 @@ class Argmin(PrimitiveWithInfer):
class ArgMaxWithValue(PrimitiveWithInfer):
"""
Calculates maximum value with corresponding index.
Calculates the maximum value with the corresponding index.
Calculates maximum value along with given axis for the input tensor. Returns the maximum values and indices.
Calculates the maximum value along with the given axis for the input tensor. It returns the maximum values and
indices.
Note:
In auto_parallel and semi_auto_parallel mode, the first output index can not be used.
Args:
axis (int): The dimension to reduce. Default: 0.
keep_dims (bool): Whether to reduce dimension, if true the output will keep same dimension with the input,
keep_dims (bool): Whether to reduce dimension, if true, the output will keep same dimension with the input,
the output will reduce dimension if false. Default: False.
Inputs:
@ -1258,11 +1259,12 @@ class ArgMaxWithValue(PrimitiveWithInfer):
:math:`(x_1, x_2, ..., x_N)`.
Outputs:
tuple(Tensor), tuple of 2 tensors, corresponding index and maximum value of input tensor.
- index (Tensor) - The index for maximum value of input tensor. If `keep_dims` is true, the output tensors shape
is :math:`(x_1, x_2, ..., x_{axis-1}, 1, x_{axis+1}, ..., x_N)`. Else, the shape is
tuple (Tensor), tuple of 2 tensors, containing the corresponding index and the maximum value of the input
tensor.
- index (Tensor) - The index for the maximum value of the input tensor. If `keep_dims` is true, the shape of
output tensors is :math:`(x_1, x_2, ..., x_{axis-1}, 1, x_{axis+1}, ..., x_N)`. Otherwise, the shape is
:math:`(x_1, x_2, ..., x_{axis-1}, x_{axis+1}, ..., x_N)`.
- output_x (Tensor) - The maximum value of input tensor, the shape same as index.
- output_x (Tensor) - The maximum value of input tensor, with the same shape as index.
Examples:
>>> input_x = Tensor(np.random.rand(5), mindspore.float32)
@ -1291,16 +1293,17 @@ class ArgMaxWithValue(PrimitiveWithInfer):
class ArgMinWithValue(PrimitiveWithInfer):
"""
Calculates minimum value with corresponding index, return indices and values.
Calculates the minimum value with corresponding index, return indices and values.
Calculates minimum value along with given axis for the input tensor. Returns the minimum values and indices.
Calculates the minimum value along with the given axis for the input tensor. It returns the minimum values and
indices.
Note:
In auto_parallel and semi_auto_parallel mode, the first output index can not be used.
Args:
axis (int): The dimension to reduce. Default: 0.
keep_dims (bool): Whether to reduce dimension, if true the output will keep same dimension as the input,
keep_dims (bool): Whether to reduce dimension, if true the output will keep the same dimension as the input,
the output will reduce dimension if false. Default: False.
Inputs:
@ -1308,9 +1311,12 @@ class ArgMinWithValue(PrimitiveWithInfer):
:math:`(x_1, x_2, ..., x_N)`.
Outputs:
Tensor, corresponding index and minimum value of input tensor. If `keep_dims` is true, the output tensors shape
is :math:`(x_1, x_2, ..., x_{axis-1}, 1, x_{axis+1}, ..., x_N)`. Else, the shape is
tuple (Tensor), tuple of 2 tensors, containing the corresponding index and the minimum value of the input
tensor.
- index (Tensor) - The index for the maximum value of the input tensor. If `keep_dims` is true, the shape of
output tensors is :math:`(x_1, x_2, ..., x_{axis-1}, 1, x_{axis+1}, ..., x_N)`. Otherwise, the shape is
:math:`(x_1, x_2, ..., x_{axis-1}, x_{axis+1}, ..., x_N)`.
- output_x (Tensor) - The minimum value of input tensor, with the same shape as index.
Examples:
>>> input_x = Tensor(np.random.rand(5))
@ -1587,9 +1593,9 @@ class Concat(PrimitiveWithInfer):
Note:
The input data is a tuple of tensors. These tensors have the same rank `R`. Set the given axis as `m`, and
:math:`0 \le m < N`. Set the number of input tensors as `N`. For the :math:`i`-th tensor :math:`t_i` has
the shape :math:`(x_1, x_2, ..., x_{mi}, ..., x_R)`. :math:`x_{mi}` is the :math:`m`-th dimension of the
:math:`i`-th tensor. Then, the output tensor shape is
:math:`0 \le m < N`. Set the number of input tensors as `N`. For the :math:`i`-th tensor :math:`t_i`, it has
the shape of :math:`(x_1, x_2, ..., x_{mi}, ..., x_R)`. :math:`x_{mi}` is the :math:`m`-th dimension of the
:math:`i`-th tensor. Then, the shape of the output tensor is
.. math::
(x_1, x_2, ..., \sum_{i=1}^Nx_{mi}, ..., x_R)
@ -1598,7 +1604,7 @@ class Concat(PrimitiveWithInfer):
axis (int): The specified axis. Default: 0.
Inputs:
- **input_x** (tuple, list) - Tuple or list of input tensors.
- **input_x** (tuple, list) - A tuple or a list of input tensors.
Outputs:
Tensor, the shape is :math:`(x_1, x_2, ..., \sum_{i=1}^Nx_{mi}, ..., x_R)`.
@ -1710,7 +1716,7 @@ class Pack(PrimitiveWithInfer):
Packs the list of input tensors with the same rank `R`, output is a tensor of rank `(R+1)`.
Given input tensors of shape :math:`(x_1, x_2, ..., x_R)`. Set the number of input tensors as `N`.
If :math:`0 \le axis`, the output tensor shape is :math:`(x_1, x_2, ..., x_{axis}, N, x_{axis+1}, ..., x_R)`.
If :math:`0 \le axis`, the shape of the output tensor is :math:`(x_1, x_2, ..., x_{axis}, N, x_{axis+1}, ..., x_R)`.
Args:
axis (int): Dimension along which to pack. Default: 0.
@ -2383,7 +2389,7 @@ class ScatterNd(PrimitiveWithInfer):
Inputs:
- **indices** (Tensor) - The index of scattering in the new tensor. With int32 data type.
- **update** (Tensor) - The source Tensor to be scattered.
- **shape** (tuple[int]) - Define the shape of the output tensor. Has the same type as indices.
- **shape** (tuple[int]) - Define the shape of the output tensor, has the same type as indices.
Outputs:
Tensor, the new tensor, has the same type as `update` and the same shape as `shape`.
@ -3074,7 +3080,7 @@ class SpaceToBatch(PrimitiveWithInfer):
of the input are zero padded according to paddings if necessary.
Args:
block_size (int): The block size of dividing block with value >= 2.
block_size (int): The block size of division, has the value not less than 2.
paddings (list): The padding value for H and W dimension, containing 2 sub list, each containing 2 int value.
All values must be >= 0. paddings[i] specifies the paddings for spatial dimension i, which corresponds to
input dimension i+2. It is required that input_shape[i+2]+paddings[i][0]+paddings[i][1] is divisible
@ -3085,7 +3091,7 @@ class SpaceToBatch(PrimitiveWithInfer):
Outputs:
Tensor, the output tensor with the same type as input. Assume input shape is :math:`(n, c, h, w)` with
:math:`block\_size` and :math:`padddings`. The output tensor shape will be :math:`(n', c', h', w')`, where
:math:`block\_size` and :math:`paddings`. The shape of the output tensor will be :math:`(n', c', h', w')`, where
:math:`n' = n*(block\_size*block\_size)`
@ -3143,11 +3149,12 @@ class BatchToSpace(PrimitiveWithInfer):
dimension and block_size with given amount to crop from dimension, respectively.
Args:
block_size (int): The block size of dividing block with value >= 2.
crops (Union[list(int), tuple(int)]): The crop value for H and W dimension, containing 2 sub list,
each containing 2 int value.
All values must be >= 0. crops[i] specifies the crop values for spatial dimension i, which corresponds to
input dimension i+2. It is required that input_shape[i+2]*block_size >= crops[i][0]+crops[i][1].
block_size (int): The block size of division, has the value not less than 2.
crops (Union[list(int), tuple(int)]): The crop value for H and W dimension, containing 2 sub lists.
Each list contains 2 integers.
All values must be not less than 0. crops[i] specifies the crop values for the spatial dimension i, which
corresponds to the input dimension i+2. It is required that
input_shape[i+2]*block_size >= crops[i][0]+crops[i][1].
Inputs:
- **input_x** (Tensor) - The input tensor. It must be a 4-D tensor, dimension 0 should be divisible by
@ -3229,7 +3236,8 @@ class SpaceToBatchND(PrimitiveWithInfer):
- **input_x** (Tensor) - The input tensor. It must be a 4-D tensor.
Outputs:
Tensor, the output tensor with the same type as input. Assume input shape is :math:`(n, c, h, w)` with
:math:`block\_shape` and :math:`padddings`. The output tensor shape will be :math:`(n', c', h', w')`, where
:math:`block\_shape` and :math:`padddings`. The shape of the output tensor will be :math:`(n', c', h', w')`,
where
:math:`n' = n*(block\_shape[0]*block\_shape[1])`
@ -3295,11 +3303,11 @@ class SpaceToBatchND(PrimitiveWithInfer):
class BatchToSpaceND(PrimitiveWithInfer):
r"""
Divide batch dimension with blocks and interleaves these blocks back into spatial dimensions.
Divide batch dimension with blocks and interleave these blocks back into spatial dimensions.
This operation will divide batch dimension N into blocks with block_shape, the output tensor's N dimension
is the corresponding number of blocks after division. The output tensor's H, W dimension is product of original H, W
dimension and block_shape with given amount to crop from dimension, respectively.
dimension and block_shape with given amount to crop from dimension, respectively.B
Args:
block_shape (Union[list(int), tuple(int)]): The block shape of dividing block with all value >= 1.

26
mindspore/ops/operations/comm_ops.py
View File

@ -47,17 +47,17 @@ class AllReduce(PrimitiveWithInfer):
Note:
The operation of AllReduce does not support "prod" currently.
Tensor must have same shape and format in all processes participating in the collective.
The tensors must have the same shape and format in all processes of the collection.
Args:
op (str): Specifies an operation used for element-wise reductions,
like sum, max, min. Default: ReduceOp.SUM.
like sum, max, and min. Default: ReduceOp.SUM.
group (str): The communication group to work on. Default: "hccl_world_group".
Raises:
TypeError: If any of op and group is not a string
or fusion is not a integer or the input's dtype is bool.
ValueError: If op is "prod"
TypeError: If any of operation and group is not a string,
or fusion is not an integer, or the input's dtype is bool.
ValueError: If the operation is "prod".
Inputs:
- **input_x** (Tensor) - The shape of tensor is :math:`(x_1, x_2, ..., x_R)`.
@ -113,7 +113,7 @@ class AllGather(PrimitiveWithInfer):
Gathers tensors from the specified communication group.
Note:
Tensor must have the same shape and format in all processes participating in the collective.
The tensors must have the same shape and format in all processes of the collection.
Args:
group (str): The communication group to work on. Default: "hccl_world_group".
@ -177,7 +177,7 @@ class _HostAllGather(PrimitiveWithInfer):
Gathers tensors from the specified communication group on host.
Note:
Tensor must have the same shape and format in all processes participating in the collective.
The tensors must have the same shape and format in all processes of the collection.
_HostAllGather is a host-side operator, it depends on OpenMPI and must use build option -M on
to enable it. Using mpirun command to run it:
mpirun -output-filename log -merge-stderr-to-stdout -np 3 python test_host_all_gather.py
@ -227,8 +227,8 @@ class ReduceScatter(PrimitiveWithInfer):
Reduces and scatters tensors from the specified communication group.
Note:
The back propagation of the op is not surported yet. Stay tuned for more.
Tensor must have the same shape and format in all processes participating in the collective.
The back propagation of the op is not supported yet. Stay tuned for more.
The tensors must have the same shape and format in all processes of the collection.
Args:
op (str): Specifies an operation used for element-wise reductions,
@ -236,7 +236,7 @@ class ReduceScatter(PrimitiveWithInfer):
group (str): The communication group to work on. Default: "hccl_world_group".
Raises:
TypeError: If any of op and group is not a string
TypeError: If any of operation and group is not a string.
ValueError: If the first dimension of input can not be divided by rank size.
Examples:
@ -288,7 +288,7 @@ class _HostReduceScatter(PrimitiveWithInfer):
Reduces and scatters tensors from the specified communication group on host.
Note:
Tensor must have the same shape and format in all processes participating in the collective.
The tensors must have the same shape and format in all processes of the collection.
_HostReduceScatter is a host-side operator, it depends on OpenMPI and must use build option
-M on to enable it. Using mpirun command to run it:
mpirun -output-filename log -merge-stderr-to-stdout -np 3 python test_host_reduce_scatter.py
@ -337,7 +337,7 @@ class Broadcast(PrimitiveWithInfer):
Broadcasts the tensor to the whole group.
Note:
Tensor must have the same shape and format in all processes participating in the collective.
The tensors must have the same shape and format in all processes of the collection.
Args:
root_rank (int): Source rank. Required in all processes except the one
@ -402,7 +402,7 @@ class _AlltoAll(PrimitiveWithInfer):
- The gather phase: Each process concatenates the received blocks along the concat_dimension.
Note:
Tensor must have the same shape and format in all processes participating in the collective.
The tensors must have the same shape and format in all processes of the collection.
Args:
split_count (int): On each process, divide blocks into split_count number.

84
mindspore/ops/operations/math_ops.py
View File

@ -131,7 +131,7 @@ class TensorAdd(_MathBinaryOp):
a bool when the first input is a tensor or a tensor whose data type is number or bool.
Outputs:
Tensor, the shape is the same as the shape after broadcasting,
Tensor, the shape is the same as the one after broadcasting,
and the data type is the one with high precision or high digits among the two inputs.
Examples:
@ -687,12 +687,12 @@ class BatchMatMul(MatMul):
`result[..., :, :] = tensor(a[..., :, :]) * tensor(b[..., :, :])`.
The two input tensors must have same rank and the rank must be `3` at least.
The two input tensors must have the same rank and the rank must be not less than `3`.
Args:
transpose_a (bool): If True, `a` is transposed on the last two dimensions before multiplication.
transpose_a (bool): If True, the last two dimensions of `a` is transposed before multiplication.
Default: False.
transpose_b (bool): If True, `b` is transposed on the last two dimensions before multiplication.
transpose_b (bool): If True, the last two dimensions of `b` is transposed before multiplication.
Default: False.
Inputs:
@ -859,11 +859,11 @@ class AccumulateNV2(PrimitiveWithInfer):
"""
Computes accumulation of all input tensors element-wise.
AccumulateNV2 is like AddN with a significant difference: AccumulateNV2 won't
wait for all of its inputs to be ready before beginning to sum. That is to say,
AccumulateNV2 will be able to save memory when inputs are ready at different
times since minimum temporary storage is proportional to the output size rather
than the inputs size.
AccumulateNV2 is similar to AddN, but there is a significant difference
among them: AccumulateNV2 will not wait for all of its inputs to be ready
before summing. That is to say, AccumulateNV2 is able to save
memory when inputs are ready at different time since the minimum temporary
storage is proportional to the output size rather than the input size.
Inputs:
- **input_x** (Union(tuple[Tensor], list[Tensor])) - The input tuple or list
@ -1085,7 +1085,7 @@ class Sub(_MathBinaryOp):
a bool when the first input is a tensor or a tensor whose data type is number or bool.
Outputs:
Tensor, the shape is the same as the shape after broadcasting,
Tensor, the shape is the same as the one after broadcasting,
and the data type is the one with high precision or high digits among the two inputs.
Examples:
@ -1124,7 +1124,7 @@ class Mul(_MathBinaryOp):
a bool when the first input is a tensor or a tensor whose data type is number or bool.
Outputs:
Tensor, the shape is the same as the shape after broadcasting,
Tensor, the shape is the same as the one after broadcasting,
and the data type is the one with high precision or high digits among the two inputs.
Examples:
@ -1164,7 +1164,7 @@ class SquaredDifference(_MathBinaryOp):
float16, float32, int32 or bool.
Outputs:
Tensor, the shape is the same as the shape after broadcasting,
Tensor, the shape is the same as the one after broadcasting,
and the data type is the one with high precision or high digits among the two inputs.
Examples:
@ -1350,7 +1350,7 @@ class Pow(_MathBinaryOp):
a bool when the first input is a tensor or a tensor whose data type is number or bool.
Outputs:
Tensor, the shape is the same as the shape after broadcasting,
Tensor, the shape is the same as the one after broadcasting,
and the data type is the one with high precision or high digits among the two inputs.
Examples:
@ -1636,7 +1636,7 @@ class Minimum(_MathBinaryOp):
a bool when the first input is a tensor or a tensor whose data type is number or bool.
Outputs:
Tensor, the shape is the same as the shape after broadcasting,
Tensor, the shape is the same as the one after broadcasting,
and the data type is the one with high precision or high digits among the two inputs.
Examples:
@ -1675,7 +1675,7 @@ class Maximum(_MathBinaryOp):
a bool when the first input is a tensor or a tensor whose data type is number or bool.
Outputs:
Tensor, the shape is the same as the shape after broadcasting,
Tensor, the shape is the same as the one after broadcasting,
and the data type is the one with high precision or high digits among the two inputs.
Examples:
@ -1714,7 +1714,7 @@ class RealDiv(_MathBinaryOp):
a bool when the first input is a tensor or a tensor whose data type is number or bool.
Outputs:
Tensor, the shape is the same as the shape after broadcasting,
Tensor, the shape is the same as the one after broadcasting,
and the data type is the one with high precision or high digits among the two inputs.
Examples:
@ -1754,7 +1754,7 @@ class Div(_MathBinaryOp):
is a number or a bool, the second input should be a tensor whose data type is number or bool.
Outputs:
Tensor, the shape is the same as the shape after broadcasting,
Tensor, the shape is the same as the one after broadcasting,
and the data type is the one with high precision or high digits among the two inputs.
Raises:
@ -1795,7 +1795,7 @@ class DivNoNan(_MathBinaryOp):
a bool when the first input is a tensor or a tensor whose data type is number or bool.
Outputs:
Tensor, the shape is the same as the shape after broadcasting,
Tensor, the shape is the same as the one after broadcasting,
and the data type is the one with high precision or high digits among the two inputs.
Raises:
@ -1838,7 +1838,7 @@ class FloorDiv(_MathBinaryOp):
a bool when the first input is a tensor or a tensor whose data type is number or bool.
Outputs:
Tensor, the shape is the same as the shape after broadcasting,
Tensor, the shape is the same as the one after broadcasting,
and the data type is the one with high precision or high digits among the two inputs.
Examples:
@ -1869,7 +1869,7 @@ class TruncateDiv(_MathBinaryOp):
a bool when the first input is a tensor or a tensor whose data type is number or bool.
Outputs:
Tensor, the shape is the same as the shape after broadcasting,
Tensor, the shape is the same as the one after broadcasting,
and the data type is the one with high precision or high digits among the two inputs.
Examples:
@ -1899,7 +1899,7 @@ class TruncateMod(_MathBinaryOp):
a bool when the first input is a tensor or a tensor whose data type is number or bool.
Outputs:
Tensor, the shape is the same as the shape after broadcasting,
Tensor, the shape is the same as the one after broadcasting,
and the data type is the one with high precision or high digits among the two inputs.
Examples:
@ -1927,7 +1927,7 @@ class Mod(_MathBinaryOp):
the second input should be a tensor whose data type is number.
Outputs:
Tensor, the shape is the same as the shape after broadcasting,
Tensor, the shape is the same as the one after broadcasting,
and the data type is the one with high precision or high digits among the two inputs.
Raises:
@ -1995,7 +1995,7 @@ class FloorMod(_MathBinaryOp):
a bool when the first input is a tensor or a tensor whose data type is number or bool.
Outputs:
Tensor, the shape is the same as the shape after broadcasting,
Tensor, the shape is the same as the one after broadcasting,
and the data type is the one with high precision or high digits among the two inputs.
Examples:
@ -2054,7 +2054,7 @@ class Xdivy(_MathBinaryOp):
a bool when the first input is a tensor or a tensor whose data type is float16, float32 or bool.
Outputs:
Tensor, the shape is the same as the shape after broadcasting,
Tensor, the shape is the same as the one after broadcasting,
and the data type is the one with high precision or high digits among the two inputs.
Examples:
@ -2089,7 +2089,7 @@ class Xlogy(_MathBinaryOp):
The value must be positive.
Outputs:
Tensor, the shape is the same as the shape after broadcasting,
Tensor, the shape is the same as the one after broadcasting,
and the data type is the one with high precision or high digits among the two inputs.
Examples:
@ -2106,7 +2106,7 @@ class Xlogy(_MathBinaryOp):
class Acosh(PrimitiveWithInfer):
"""
Compute inverse hyperbolic cosine of x element-wise.
Compute inverse hyperbolic cosine of the input element-wise.
Inputs:
- **input_x** (Tensor) - The shape of tensor is :math:`(x_1, x_2, ..., x_R)`.
@ -2163,7 +2163,7 @@ class Cosh(PrimitiveWithInfer):
class Asinh(PrimitiveWithInfer):
"""
Compute inverse hyperbolic sine of x element-wise.
Compute inverse hyperbolic sine of the input element-wise.
Inputs:
- **input_x** (Tensor) - The shape of tensor is :math:`(x_1, x_2, ..., x_R)`.
@ -2250,7 +2250,7 @@ class Equal(_LogicBinaryOp):
a bool when the first input is a tensor or a tensor whose data type is number or bool.
Outputs:
Tensor, the shape is the same as the shape after broadcasting,and the data type is bool.
Tensor, the shape is the same as the one after broadcasting,and the data type is bool.
Examples:
>>> input_x = Tensor(np.array([1, 2, 3]), mindspore.float32)
@ -2271,7 +2271,7 @@ class Equal(_LogicBinaryOp):
class ApproximateEqual(_LogicBinaryOp):
"""
Returns the truth value of abs(x1-x2) < tolerance element-wise.
Returns true if abs(x1-x2) is smaller than tolerance element-wise, otherwise false.
Inputs of `x1` and `x2` comply with the implicit type conversion rules to make the data types consistent.
If they have different data types, lower priority data type will be converted to
@ -2316,7 +2316,7 @@ class EqualCount(PrimitiveWithInfer):
"""
Computes the number of the same elements of two tensors.
The two input tensors should have same data type and shape.
The two input tensors should have the same data type and shape.
Inputs:
- **input_x** (Tensor) - The first input tensor.
@ -2365,7 +2365,7 @@ class NotEqual(_LogicBinaryOp):
a bool when the first input is a tensor or a tensor whose data type is number or bool.
Outputs:
Tensor, the shape is the same as the shape after broadcasting,and the data type is bool.
Tensor, the shape is the same as the one after broadcasting,and the data type is bool.
Examples:
>>> input_x = Tensor(np.array([1, 2, 3]), mindspore.float32)
@ -2402,7 +2402,7 @@ class Greater(_LogicBinaryOp):
a bool when the first input is a tensor or a tensor whose data type is number or bool.
Outputs:
Tensor, the shape is the same as the shape after broadcasting,and the data type is bool.
Tensor, the shape is the same as the one after broadcasting,and the data type is bool.
Examples:
>>> input_x = Tensor(np.array([1, 2, 3]), mindspore.int32)
@ -2439,7 +2439,7 @@ class GreaterEqual(_LogicBinaryOp):
a bool when the first input is a tensor or a tensor whose data type is number or bool.
Outputs:
Tensor, the shape is the same as the shape after broadcasting,and the data type is bool.
Tensor, the shape is the same as the one after broadcasting,and the data type is bool.
Examples:
>>> input_x = Tensor(np.array([1, 2, 3]), mindspore.int32)
@ -2476,7 +2476,7 @@ class Less(_LogicBinaryOp):
a bool when the first input is a tensor or a tensor whose data type is number or bool.
Outputs:
Tensor, the shape is the same as the shape after broadcasting,and the data type is bool.
Tensor, the shape is the same as the one after broadcasting,and the data type is bool.
Examples:
>>> input_x = Tensor(np.array([1, 2, 3]), mindspore.int32)
@ -2513,7 +2513,7 @@ class LessEqual(_LogicBinaryOp):
a bool when the first input is a tensor or a tensor whose data type is number or bool.
Outputs:
Tensor, the shape is the same as the shape after broadcasting,and the data type is bool.
Tensor, the shape is the same as the one after broadcasting,and the data type is bool.
Examples:
>>> input_x = Tensor(np.array([1, 2, 3]), mindspore.int32)
@ -2579,7 +2579,7 @@ class LogicalAnd(_LogicBinaryOp):
a tensor whose data type is bool.
Outputs:
Tensor, the shape is the same as the shape after broadcasting, and the data type is bool.
Tensor, the shape is the same as the one after broadcasting, and the data type is bool.
Examples:
>>> input_x = Tensor(np.array([True, False, True]), mindspore.bool_)
@ -2610,7 +2610,7 @@ class LogicalOr(_LogicBinaryOp):
a tensor whose data type is bool.
Outputs:
Tensor, the shape is the same as the shape after broadcasting,and the data type is bool.
Tensor, the shape is the same as the one after broadcasting,and the data type is bool.
Examples:
>>> input_x = Tensor(np.array([True, False, True]), mindspore.bool_)
@ -3159,13 +3159,13 @@ class Tan(PrimitiveWithInfer):
class Atan(PrimitiveWithInfer):
"""
Computes the trignometric inverse tangent of x element-wise.
Computes the trigonometric inverse tangent of the input element-wise.
Inputs:
- **input_x** (Tensor): The input tensor.
Outputs:
A Tensor. Has the same type as x.
A Tensor, has the same type as the input.
Examples:
>>> input_x = Tensor(np.array([1.047, 0.785]), mindspore.float32)
@ -3190,13 +3190,13 @@ class Atan(PrimitiveWithInfer):
class Atanh(PrimitiveWithInfer):
"""
Computes inverse hyperbolic tangent of x element-wise.
Computes inverse hyperbolic tangent of the input element-wise.
Inputs:
- **input_x** (Tensor): The input tensor.
Outputs:
A Tensor. Has the same type as x.
A Tensor, has the same type as the input.
Examples:
>>> input_x = Tensor(np.array([1.047, 0.785]), mindspore.float32)
@ -3234,7 +3234,7 @@ class Atan2(_MathBinaryOp):
- **input_y** (Tensor) - The input tensor.
Outputs:
Tensor, the shape is the same as the shape after broadcasting,and the data type is same as `input_x`.
Tensor, the shape is the same as the one after broadcasting,and the data type is same as `input_x`.
Examples:
>>> input_x = Tensor(np.array([[0, 1]]), mindspore.float32)

180
mindspore/ops/operations/nn_ops.py
View File

@ -740,7 +740,7 @@ class BNTrainingReduce(PrimitiveWithInfer):
class BNTrainingUpdate(PrimitiveWithInfer):
"""
primitive operator of bn_training_update's register and info descriptor
The primitive operator of the register and info descriptor in bn_training_update.
"""
@prim_attr_register
def __init__(self, isRef=True, epsilon=1e-5, factor=0.1):
@ -1511,9 +1511,9 @@ class BiasAdd(PrimitiveWithInfer):
except for the channel axis.
Inputs:
- **input_x** (Tensor) - Input value. The input shape can be 2-4 dimensions.
- **bias** (Tensor) - Bias value, with shape :math:`(C)`.
The shape of `bias` must be the same as `input_x` in second dimension.
- **input_x** (Tensor) - The input tensor. The shape can be 2-4 dimensions.
- **bias** (Tensor) - The bias tensor, with shape :math:`(C)`.
The shape of `bias` must be the same as `input_x` in the second dimension.
Outputs:
Tensor, with the same shape and type as `input_x`.
@ -1604,7 +1604,7 @@ class SoftmaxCrossEntropyWithLogits(PrimitiveWithInfer):
Inputs:
- **logits** (Tensor) - Input logits, with shape :math:`(N, C)`. Data type should be float16 or float32.
- **labels** (Tensor) - Ground truth labels, with shape :math:`(N, C)`. Has the same data type with `logits`.
- **labels** (Tensor) - Ground truth labels, with shape :math:`(N, C)`, has the same data type with `logits`.
Outputs:
Tuple of 2 Tensor, the loss shape is `(N,)`, and the dlogits with the same shape as `logits`.
@ -1816,7 +1816,7 @@ class L2Loss(PrimitiveWithInfer):
- **input_x** (Tensor) - A input Tensor. Data type should be float16 or float32.
Outputs:
Tensor. Has the same dtype as `input_x`. The output tensor is the value of loss which is a scalar tensor.
Tensor, has the same dtype as `input_x`. The output tensor is the value of loss which is a scalar tensor.
Examples
>>> input_x = Tensor(np.array([1, 2, 3]), mindspore.float16)
@ -2023,7 +2023,7 @@ class ApplyRMSProp(PrimitiveWithInfer):
.. math::
w = w - m_{t}
where, :math:`w` represents `var`, which will be updated.
where :math:`w` represents `var`, which will be updated.
:math:`s_{t}` represents `mean_square`, :math:`s_{t-1}` is the last momentent of :math:`s_{t}`,
:math:`m_{t}` represents `moment`, :math:`m_{t-1}` is the last momentent of :math:`m_{t}`.
:math:`\\rho` represents `decay`. :math:`\\beta` is the momentum term, represents `momentum`.
@ -2117,7 +2117,7 @@ class ApplyCenteredRMSProp(PrimitiveWithInfer):
.. math::
w = w - m_{t}
where, :math:`w` represents `var`, which will be updated.
where :math:`w` represents `var`, which will be updated.
:math:`g_{t}` represents `mean_gradient`, :math:`g_{t-1}` is the last momentent of :math:`g_{t}`.
:math:`s_{t}` represents `mean_square`, :math:`s_{t-1}` is the last momentent of :math:`s_{t}`,
:math:`m_{t}` represents `moment`, :math:`m_{t-1}` is the last momentent of :math:`m_{t}`.
@ -2985,7 +2985,7 @@ class Adam(PrimitiveWithInfer):
`epsilon`.
Args:
use_locking (bool): Whether to enable a lock to protect updating variable tensors.
use_locking (bool): Whether to enable a lock to protect variable tensors from being updated.
If true, updates of the var, m, and v tensors will be protected by a lock.
If false, the result is unpredictable. Default: False.
use_nesterov (bool): Whether to use Nesterov Accelerated Gradient (NAG) algorithm to update the gradients.
@ -2994,16 +2994,16 @@ class Adam(PrimitiveWithInfer):
Inputs:
- **var** (Tensor) - Weights to be updated.
- **m** (Tensor) - The 1st moment vector in the updating formula. Has the same type as `var`.
- **m** (Tensor) - The 1st moment vector in the updating formula, has the same type as `var`.
- **v** (Tensor) - the 2nd moment vector in the updating formula.
Mean square gradients, has the same type as `var`.
Mean square gradients with the same type as `var`.
- **beta1_power** (float) - :math:`beta_1^t` in the updating formula.
- **beta2_power** (float) - :math:`beta_2^t` in the updating formula.
- **lr** (float) - :math:`l` in the updating formula.
- **beta1** (float) - The exponential decay rate for the 1st moment estimations.
- **beta2** (float) - The exponential decay rate for the 2nd moment estimations.
- **epsilon** (float) - Term added to the denominator to improve numerical stability.
- **gradient** (Tensor) - Gradients. Has the same type as `var`.
- **gradient** (Tensor) - Gradients, has the same type as `var`.
Outputs:
Tuple of 3 Tensor, the updated parameters.
@ -3084,7 +3084,7 @@ class FusedSparseAdam(PrimitiveWithInfer):
RuntimeError exception will be thrown when the data type conversion of Parameter is required.
Args:
use_locking (bool): Whether to enable a lock to protect updating variable tensors.
use_locking (bool): Whether to enable a lock to protect variable tensors from being updated.
If true, updates of the var, m, and v tensors will be protected by a lock.
If false, the result is unpredictable. Default: False.
use_nesterov (bool): Whether to use Nesterov Accelerated Gradient (NAG) algorithm to update the gradients.
@ -3093,10 +3093,10 @@ class FusedSparseAdam(PrimitiveWithInfer):
Inputs:
- **var** (Parameter) - Parameters to be updated. With float32 data type.
- **m** (Parameter) - The 1st moment vector in the updating formula. Has the same type as `var`. With
- **m** (Parameter) - The 1st moment vector in the updating formula, has the same type as `var`. With
float32 data type.
- **v** (Parameter) - The 2nd moment vector in the updating formula. Mean square gradients,
has the same type as `var`. With float32 data type.
- **v** (Parameter) - The 2nd moment vector in the updating formula. Mean square gradients
with the same type as `var`. With float32 data type.
- **beta1_power** (Tensor) - :math:`beta_1^t` in the updating formula. With float32 data type.
- **beta2_power** (Tensor) - :math:`beta_2^t` in the updating formula. With float32 data type.
- **lr** (Tensor) - :math:`l` in the updating formula. With float32 data type.
@ -3217,7 +3217,7 @@ class FusedSparseLazyAdam(PrimitiveWithInfer):
RuntimeError exception will be thrown when the data type conversion of Parameter is required.
Args:
use_locking (bool): Whether to enable a lock to protect updating variable tensors.
use_locking (bool): Whether to enable a lock to protect variable tensors from being updated.
If true, updates of the var, m, and v tensors will be protected by a lock.
If false, the result is unpredictable. Default: False.
use_nesterov (bool): Whether to use Nesterov Accelerated Gradient (NAG) algorithm to update the gradients.
@ -3226,10 +3226,10 @@ class FusedSparseLazyAdam(PrimitiveWithInfer):
Inputs:
- **var** (Parameter) - Parameters to be updated. With float32 data type.
- **m** (Parameter) - The 1st moment vector in the updating formula. Has the same type as `var`. With
- **m** (Parameter) - The 1st moment vector in the updating formula, has the same type as `var`. With
float32 data type.
- **v** (Parameter) - The 2nd moment vector in the updating formula. Mean square gradients,
has the same type as `var`. With float32 data type.
- **v** (Parameter) - The 2nd moment vector in the updating formula. Mean square gradients
with the same type as `var`. With float32 data type.
- **beta1_power** (Tensor) - :math:`beta_1^t` in the updating formula. With float32 data type.
- **beta2_power** (Tensor) - :math:`beta_2^t` in the updating formula. With float32 data type.
- **lr** (Tensor) - :math:`l` in the updating formula. With float32 data type.
@ -3340,8 +3340,8 @@ class FusedSparseFtrl(PrimitiveWithInfer):
Inputs:
- **var** (Parameter) - The variable to be updated. The data type must be float32.
- **accum** (Parameter) - The accum to be updated, must be same type and shape as `var`.
- **linear** (Parameter) - The linear to be updated, must be same type and shape as `var`.
- **accum** (Parameter) - The accumulation to be updated, must be same type and shape as `var`.
- **linear** (Parameter) - the linear coefficient to be updated, must be same type and shape as `var`.
- **grad** (Tensor) - A tensor of the same type as `var`, for the gradient.
- **indices** (Tensor) - A vector of indices into the first dimension of `var` and `accum`. The shape
of `indices` must be the same as `grad` in first dimension. The type must be int32.
@ -3434,11 +3434,12 @@ class FusedSparseProximalAdagrad(PrimitiveWithInfer):
RuntimeError exception will be thrown when the data type conversion of Parameter is required.
Args:
use_locking (bool): If true, updates of the var and accum tensors will be protected. Default: False.
use_locking (bool): If true, the var and accumulation tensors will be protected from being updated.
Default: False.
Inputs:
- **var** (Parameter) - Variable tensor to be updated. The data type must be float32.
- **accum** (Parameter) - Variable tensor to be updated. Has the same dtype as `var`.
- **accum** (Parameter) - Variable tensor to be updated, has the same dtype as `var`.
- **lr** (Tensor) - The learning rate value. The data type must be float32.
- **l1** (Tensor) - l1 regularization strength. The data type must be float32.
- **l2** (Tensor) - l2 regularization strength. The data type must be float32.
@ -3595,9 +3596,9 @@ class BinaryCrossEntropy(PrimitiveWithInfer):
.. math::
\ell(x, y) = \begin{cases}
L, & \text{if reduction} = \text{'none';}\\
\operatorname{mean}(L), & \text{if reduction} = \text{'mean';}\\
\operatorname{sum}(L), & \text{if reduction} = \text{'sum'.}
L, & \text{if reduction} = \text{`none';}\\
\operatorname{mean}(L), & \text{if reduction} = \text{`mean';}\\
\operatorname{sum}(L), & \text{if reduction} = \text{`sum'.}
\end{cases}
Args:
@ -3611,8 +3612,8 @@ class BinaryCrossEntropy(PrimitiveWithInfer):
And it should have same shape and data type as `input_x`. Default: None.
Outputs:
Tensor or Scalar, if `reduction` is 'none', then output is a tensor and same shape as `input_x`.
Otherwise it is a scalar.
Tensor or Scalar, if `reduction` is 'none', then output is a tensor and has the same shape as `input_x`.
Otherwise, the output is a scalar.
Examples:
>>> import mindspore
@ -3672,11 +3673,11 @@ class ApplyAdaMax(PrimitiveWithInfer):
var = var - \frac{l}{1 - \beta_1^t} * \frac{m_{t}}{v_{t} + \epsilon}
\end{array}
:math:`t` represents updating step while, :math:`m` represents the 1st moment vector, :math:`m_{t-1}`
:math:`t` represents updating step while :math:`m` represents the 1st moment vector, :math:`m_{t-1}`
is the last momentent of :math:`m_{t}`, :math:`v` represents the 2nd moment vector, :math:`v_{t-1}`
is the last momentent of :math:`v_{t}`, :math:`l` represents scaling factor `lr`,
:math:`g` represents `grad`, :math:`\beta_1, \beta_2` represent `beta1` and `beta2`,
:math:`beta_1^t` represent `beta1_power`, :math:`var` represents Variable to be updated,
:math:`beta_1^t` represents `beta1_power`, :math:`var` represents the variable to be updated,
:math:`\epsilon` represents `epsilon`.
Inputs of `var`, `m`, `v` and `grad` comply with the implicit type conversion rules
@ -3687,10 +3688,10 @@ class ApplyAdaMax(PrimitiveWithInfer):
Inputs:
- **var** (Parameter) - Variable to be updated. With float32 or float16 data type.
- **m** (Parameter) - The 1st moment vector in the updating formula. Has the same shape and type as `var`.
- **m** (Parameter) - The 1st moment vector in the updating formula, has the same shape and type as `var`.
With float32 or float16 data type.
- **v** (Parameter) - The 2nd moment vector in the updating formula. Mean square gradients,
has the same shape and type as `var`. With float32 or float16 data type.
- **v** (Parameter) - The 2nd moment vector in the updating formula. Mean square gradients
with the same shape and type as `var`. With float32 or float16 data type.
- **beta1_power** (Union[Number, Tensor]) - :math:`beta_1^t` in the updating formula, should be scalar.
With float32 or float16 data type.
- **lr** (Union[Number, Tensor]) - Learning rate, :math:`l` in the updating formula, should be scalar.
@ -3701,7 +3702,7 @@ class ApplyAdaMax(PrimitiveWithInfer):
should be scalar. With float32 or float16 data type.
- **epsilon** (Union[Number, Tensor]) - A small value added for numerical stability, should be scalar.
With float32 or float16 data type.
- **grad** (Tensor) - A tensor for gradient. Has the same shape and type as `var`.
- **grad** (Tensor) - A tensor for gradient, has the same shape and type as `var`.
With float32 or float16 data type.
Outputs:
@ -3814,13 +3815,13 @@ class ApplyAdadelta(PrimitiveWithInfer):
Inputs:
- **var** (Parameter) - Weights to be updated. With float32 or float16 data type.
- **accum** (Parameter) - Accum to be updated, has the same shape and type as `var`.
- **accum** (Parameter) - Accumulation to be updated, has the same shape and type as `var`.
With float32 or float16 data type.
- **accum_update** (Parameter) - Accum_update to be updated, has the same shape and type as `var`.
With float32 or float16 data type.
- **lr** (Union[Number, Tensor]) - Learning rate, must be scalar. With float32 or float16 data type.
- **rho** (Union[Number, Tensor]) - Decay rate, must be scalar. With float32 or float16 data type.
- **epsilon** (Union[Number, Tensor]) - A small value added for numerical stability, must be scalar.
- **lr** (Union[Number, Tensor]) - Learning rate, should be scalar. With float32 or float16 data type.
- **rho** (Union[Number, Tensor]) - Decay rate, should be scalar. With float32 or float16 data type.
- **epsilon** (Union[Number, Tensor]) - A small value added for numerical stability, should be scalar.
With float32 or float16 data type.
- **grad** (Tensor) - Gradients, has the same shape and type as `var`. With float32 or float16 data type.
@ -3919,7 +3920,7 @@ class ApplyAdagrad(PrimitiveWithInfer):
Inputs:
- **var** (Parameter) - Variable to be updated. With float32 or float16 data type.
- **accum** (Parameter) - Accum to be updated. The shape and dtype should be the same as `var`.
- **accum** (Parameter) - Accumulation to be updated. The shape and dtype should be the same as `var`.
With float32 or float16 data type.
- **lr** (Union[Number, Tensor]) - The learning rate value, should be scalar. With float32 or float16 data type.
- **grad** (Tensor) - A tensor for gradient. The shape and dtype should be the same as `var`.
@ -4001,7 +4002,7 @@ class ApplyAdagradV2(PrimitiveWithInfer):
Inputs:
- **var** (Parameter) - Variable to be updated. With float16 or float32 data type.
- **accum** (Parameter) - Accum to be updated. The shape and dtype should be the same as `var`.
- **accum** (Parameter) - Accumulation to be updated. The shape and dtype should be the same as `var`.
With float16 or float32 data type.
- **lr** (Union[Number, Tensor]) - The learning rate value, should be a float number or
a scalar tensor with float16 or float32 data type.
@ -4081,11 +4082,12 @@ class SparseApplyAdagrad(PrimitiveWithInfer):
Args:
lr (float): Learning rate.
update_slots (bool): If `True`, `accum` will be updated. Default: True.
use_locking (bool): If true, updates of the var and accum tensors will be protected. Default: False.
use_locking (bool): If true, the var and accumulation tensors will be protected from being updated.
Default: False.
Inputs:
- **var** (Parameter) - Variable to be updated. The data type must be float16 or float32.
- **accum** (Parameter) - Accum to be updated. The shape and dtype should be the same as `var`.
- **accum** (Parameter) - Accumulation to be updated. The shape and dtype should be the same as `var`.
- **grad** (Tensor) - Gradient. The shape must be the same as `var`'s shape except first dimension.
Has the same data type as `var`.
- **indices** (Tensor) - A vector of indices into the first dimension of `var` and `accum`.
@ -4166,12 +4168,13 @@ class SparseApplyAdagradV2(PrimitiveWithInfer):
Args:
lr (float): Learning rate.
epsilon (float): A small value added for numerical stability.
use_locking (bool): If `True`, updating of the var and accum tensors will be protected. Default: False.
use_locking (bool): If `True`, the var and accumulation tensors will be protected from being updated.
Default: False.
update_slots (bool): If `True`, the computation logic will be different to `False`. Default: True.
Inputs:
- **var** (Parameter) - Variable to be updated. The data type must be float16 or float32.
- **accum** (Parameter) - Accum to be updated. The shape and dtype should be the same as `var`.
- **accum** (Parameter) - Accumulation to be updated. The shape and dtype should be the same as `var`.
- **grad** (Tensor) - Gradient. The shape must be the same as `var`'s shape except first dimension.
Has the same data type as `var`.
- **indices** (Tensor) - A vector of indices into the first dimension of `var` and `accum`.
@ -4253,18 +4256,19 @@ class ApplyProximalAdagrad(PrimitiveWithInfer):
RuntimeError exception will be thrown when the data type conversion of Parameter is required.
Args:
use_locking (bool): If true, updates of the var and accum tensors will be protected. Default: False.
use_locking (bool): If true, the var and accumulation tensors will be protected from being updated.
Default: False.
Inputs:
- **var** (Parameter) - Variable to be updated. The data type should be float16 or float32.
- **accum** (Parameter) - Accum to be updated. Must has the same shape and dtype as `var`.
- **accum** (Parameter) - Accumulation to be updated. Must has the same shape and dtype as `var`.
- **lr** (Union[Number, Tensor]) - The learning rate value, should be scalar. The data type should be
float16 or float32.
- **l1** (Union[Number, Tensor]) - l1 regularization strength, should be scalar. The data type should be
float16 or float32.
- **l2** (Union[Number, Tensor]) - l2 regularization strength, should be scalar. The data type should be
float16 or float32.
- **grad** (Tensor) - Gradient. Must has the same shape and dtype as `var`.
- **grad** (Tensor) - Gradient with the same shape and dtype as `var`.
Outputs:
Tuple of 2 Tensor, the updated parameters.
@ -4355,11 +4359,12 @@ class SparseApplyProximalAdagrad(PrimitiveWithCheck):
RuntimeError exception will be thrown when the data type conversion of Parameter is required.
Args:
use_locking (bool): If true, updates of the var and accum tensors will be protected. Default: False.
use_locking (bool): If true, the var and accumulation tensors will be protected from being updated.
Default: False.
Inputs:
- **var** (Parameter) - Variable tensor to be updated. The data type must be float16 or float32.
- **accum** (Parameter) - Variable tensor to be updated. Has the same dtype as `var`.
- **accum** (Parameter) - Variable tensor to be updated, has the same dtype as `var`.
- **lr** (Union[Number, Tensor]) - The learning rate value. Tshould be a float number or
a scalar tensor with float16 or float32 data type.
- **l1** (Union[Number, Tensor]) - l1 regularization strength. should be a float number or
@ -4440,7 +4445,7 @@ class ApplyAddSign(PrimitiveWithInfer):
var = var - lr_{t} * \text{update}
\end{array}
:math:`t` represents updating step while, :math:`m` represents the 1st moment vector, :math:`m_{t-1}`
:math:`t` represents updating step while :math:`m` represents the 1st moment vector, :math:`m_{t-1}`
is the last momentent of :math:`m_{t}`, :math:`lr` represents scaling factor `lr`, :math:`g` represents `grad`.
Inputs of `var`, `accum` and `grad` comply with the implicit type conversion rules
@ -4451,7 +4456,7 @@ class ApplyAddSign(PrimitiveWithInfer):
Inputs:
- **var** (Parameter) - Variable tensor to be updated. With float32 or float16 data type.
- **m** (Parameter) - Variable tensor to be updated. Has the same dtype as `var`.
- **m** (Parameter) - Variable tensor to be updated, has the same dtype as `var`.
- **lr** (Union[Number, Tensor]) - The learning rate value, should be a scalar.
With float32 or float16 data type.
- **alpha** (Union[Number, Tensor]) - Should be a scalar. With float32 or float16 data type.
@ -4546,7 +4551,7 @@ class ApplyPowerSign(PrimitiveWithInfer):
var = var - lr_{t} * \text{update}
\end{array}
:math:`t` represents updating step while, :math:`m` represents the 1st moment vector, :math:`m_{t-1}`
:math:`t` represents updating step while :math:`m` represents the 1st moment vector, :math:`m_{t-1}`
is the last momentent of :math:`m_{t}`, :math:`lr` represents scaling factor `lr`, :math:`g` represents `grad`.
All of inputs comply with the implicit type conversion rules to make the data types consistent.
@ -4559,7 +4564,7 @@ class ApplyPowerSign(PrimitiveWithInfer):
Inputs:
- **var** (Parameter) - Variable tensor to be updated. With float32 or float16 data type.
If data type of `var` is float16, all inputs must have the same data type as `var`.
- **m** (Parameter) - Variable tensor to be updated. Has the same dtype as `var`.
- **m** (Parameter) - Variable tensor to be updated, has the same dtype as `var`.
- **lr** (Union[Number, Tensor]) - The learning rate value, should be a scalar.
With float32 or float16 data type.
- **logbase** (Union[Number, Tensor]) - Should be a scalar. With float32 or float16 data type.
@ -4659,10 +4664,10 @@ class ApplyGradientDescent(PrimitiveWithInfer):
Inputs:
- **var** (Parameter) - Variable tensor to be updated. With float32 or float16 data type.
- **alpha** (Union[Number, Tensor]) - Scaling factor, should be a scalar. With float32 or float16 data type.
- **delta** (Tensor) - A tensor for the change. Has the same type as `var`.
- **delta** (Tensor) - A tensor for the change, has the same type as `var`.
Outputs:
Tensor, representing the updated var.
Tensor, represents the updated `var`.
Examples:
>>> import numpy as np
@ -4730,10 +4735,10 @@ class ApplyProximalGradientDescent(PrimitiveWithInfer):
With float32 or float16 data type.
- **l2** (Union[Number, Tensor]) - l2 regularization strength, should be scalar.
With float32 or float16 data type.
- **delta** (Tensor) - A tensor for the change. Has the same type as `var`.
- **delta** (Tensor) - A tensor for the change, has the same type as `var`.
Outputs:
Tensor, representing the updated var.
Tensor, represents the updated `var`.
Examples:
>>> import numpy as np
@ -4812,7 +4817,7 @@ class LARSUpdate(PrimitiveWithInfer):
- **learning_rate** (Union[Number, Tensor]) - Learning rate. It should be a scalar tensor or number.
Outputs:
Tensor, representing the new gradient.
Tensor, represents the new gradient.
Examples:
>>> from mindspore import Tensor
@ -4879,8 +4884,8 @@ class ApplyFtrl(PrimitiveWithInfer):
Inputs:
- **var** (Parameter) - The variable to be updated. The data type should be float16 or float32.
- **accum** (Parameter) - The accum to be updated, must be same type and shape as `var`.
- **linear** (Parameter) - The linear to be updated, must be same type and shape as `var`.
- **accum** (Parameter) - The accumulation to be updated, must be same type and shape as `var`.
- **linear** (Parameter) - the linear coefficient to be updated, must be same type and shape as `var`.
- **grad** (Tensor) - Gradient. The data type should be float16 or float32.
- **lr** (Union[Number, Tensor]) - The learning rate value, must be positive. Default: 0.001.
It should be a float number or a scalar tensor with float16 or float32 data type.
@ -4893,7 +4898,7 @@ class ApplyFtrl(PrimitiveWithInfer):
Default: -0.5. It should be a float number or a scalar tensor with float16 or float32 data type.
Outputs:
Tensor, representing the updated var.
Tensor, represents the updated `var`.
Examples:
>>> import mindspore
@ -4975,8 +4980,8 @@ class SparseApplyFtrl(PrimitiveWithCheck):
Inputs:
- **var** (Parameter) - The variable to be updated. The data type must be float16 or float32.
- **accum** (Parameter) - The accum to be updated, must be same type and shape as `var`.
- **linear** (Parameter) - The linear to be updated, must be same type and shape as `var`.
- **accum** (Parameter) - The accumulation to be updated, must be same type and shape as `var`.
- **linear** (Parameter) - the linear coefficient to be updated, must be same type and shape as `var`.
- **grad** (Tensor) - A tensor of the same type as `var`, for the gradient.
- **indices** (Tensor) - A vector of indices into the first dimension of `var` and `accum`.
The shape of `indices` must be the same as `grad` in first dimension. The type must be int32.
@ -5062,12 +5067,13 @@ class SparseApplyFtrlV2(PrimitiveWithInfer):
l2_shrinkage (float): L2 shrinkage regularization.
lr_power (float): Learning rate power controls how the learning rate decreases during training,
must be less than or equal to zero. Use fixed learning rate if `lr_power` is zero.
use_locking (bool): If `True`, updating of the var and accum tensors will be protected. Default: False.
use_locking (bool): If `True`, the var and accumulation tensors will be protected from being updated.
Default: False.
Inputs:
- **var** (Parameter) - The variable to be updated. The data type must be float16 or float32.
- **accum** (Parameter) - The accum to be updated, must be same type and shape as `var`.
- **linear** (Parameter) - The linear to be updated, must be same type and shape as `var`.
- **accum** (Parameter) - The accumulation to be updated, must be same type and shape as `var`.
- **linear** (Parameter) - the linear coefficient to be updated, must be same type and shape as `var`.
- **grad** (Tensor) - A tensor of the same type as `var`, for the gradient.
- **indices** (Tensor) - A vector of indices into the first dimension of `var` and `accum`.
The shape of `indices` must be the same as `grad` in first dimension. The type must be int32.
@ -5277,14 +5283,14 @@ class DropoutGrad(PrimitiveWithInfer):
class CTCLoss(PrimitiveWithInfer):
"""
Calculates the CTC(Connectionist Temporal Classification) loss. Also calculates the gradient.
Calculates the CTC (Connectionist Temporal Classification) loss and the gradient.
Args:
preprocess_collapse_repeated (bool): If true, repeated labels are collapsed prior to the CTC calculation.
preprocess_collapse_repeated (bool): If true, repeated labels will be collapsed prior to the CTC calculation.
Default: False.
ctc_merge_repeated (bool): If false, during CTC calculation, repeated non-blank labels will not be merged
and are interpreted as individual labels. This is a simplfied version of CTC.
Default: True.
and these labels will be interpreted as individual ones. This is a simplfied
version of CTC. Default: True.
ignore_longer_outputs_than_inputs (bool): If True, sequences with longer outputs than inputs will be ignored.
Default: False.
@ -5295,15 +5301,15 @@ class CTCLoss(PrimitiveWithInfer):
Data type must be float32 or float64.
- **labels_indices** (Tensor) - The indices of labels. `labels_indices[i, :] == [b, t]` means `labels_values[i]`
stores the id for `(batch b, time t)`. The type must be int64 and rank must be 2.
- **labels_values** (Tensor) - A `1-D` input tensor. The values associated with the given batch and time. The
type must be int32. `labels_values[i]` must in the range of `[0, num_classes)`.
- **labels_values** (Tensor) - A `1-D` input tensor. The values are associated with the given batch and time.
The type must be int32. `labels_values[i]` must in the range of `[0, num_classes)`.
- **sequence_length** (Tensor) - A tensor containing sequence lengths with the shape of :math:`(batch_size)`.
The type must be int32. Each value in the tensor should not greater than `max_time`.
The type must be int32. Each value in the tensor should not be greater than `max_time`.
Outputs:
- **loss** (Tensor) - A tensor containing log-probabilities, the shape is :math:`(batch_size)`. Has the same
type with `inputs`.
- **gradient** (Tensor) - The gradient of `loss`. Has the same type and shape with `inputs`.
- **loss** (Tensor) - A tensor containing log-probabilities, the shape is :math:`(batch_size)`. The tensor has
the same type with `inputs`.
- **gradient** (Tensor) - The gradient of `loss`, has the same type and shape with `inputs`.
Examples:
>>> inputs = Tensor(np.random.random((2, 2, 3)), mindspore.float32)
@ -5372,7 +5378,7 @@ class CTCGreedyDecoder(PrimitiveWithInfer):
- **decoded_shape** (Tensor) - The value of tensor is :math:`[batch_size, max_decoded_legth]`.
Data type is int64.
- **log_probability** (Tensor) - A tensor with shape of :math:`(batch_size, 1)`,
containing sequence log-probability. Has the same type as `inputs`.
containing sequence log-probability, has the same type as `inputs`.
Examples:
>>> class CTCGreedyDecoderNet(nn.Cell):
@ -5417,7 +5423,7 @@ class CTCGreedyDecoder(PrimitiveWithInfer):
class BasicLSTMCell(PrimitiveWithInfer):
r"""
Performs the long short term memory(LSTM) on the input.
Applies the long short-term memory (LSTM) to the input.
.. math::
\begin{array}{ll} \\
@ -5440,10 +5446,10 @@ class BasicLSTMCell(PrimitiveWithInfer):
Args:
keep_prob (float): If not 1.0, append `Dropout` layer on the outputs of each
LSTM layer except the last layer. Default 1.0. The range of dropout is [0.0, 1.0].
forget_bias (float): Add forget bias to forget gate biases in order to decrease former scale. Default to 1.0.
state_is_tuple (bool): If true, state is tensor tuple, containing h and c; If false, one tensor,
need split first. Default to True.
activation (str): Activation. Default to "tanh". Only "tanh" is currently supported.
forget_bias (float): Add forget bias to forget gate biases in order to decrease former scale. Default: 1.0.
state_is_tuple (bool): If true, the state is a tuple of 2 tensors, containing h and c; If false, the state is
a tensor and it needs to be split first. Default: True.
activation (str): Activation. Default: "tanh". Only "tanh" is currently supported.
Inputs:
- **x** (Tensor) - Current words. Tensor of shape (`batch_size`, `input_size`).
@ -5470,7 +5476,7 @@ class BasicLSTMCell(PrimitiveWithInfer):
- **ot** (Tensor) - Forward :math:`o_t` cache at moment `t`. Tensor of shape (`batch_size`, `hidden_size`).
Has the same type with input `c`.
- **tanhct** (Tensor) - Forward :math:`tanh c_t` cache at moment `t`.
Tensor of shape (`batch_size`, `hidden_size`). Has the same type with input `c`.
Tensor of shape (`batch_size`, `hidden_size`), has the same type with input `c`.
Examples:
>>> x = Tensor(np.random.rand(1, 32).astype(np.float16))
@ -5610,7 +5616,7 @@ class LRN(PrimitiveWithInfer):
class CTCLossV2(PrimitiveWithInfer):
r"""
Calculates the CTC(Connectionist Temporal Classification) loss. Also calculates the gradient.
Calculates the CTC (Connectionist Temporal Classification) loss and the gradient.
Note:
- Cudnn Uses label value of for the `blank`
@ -5629,9 +5635,9 @@ class CTCLossV2(PrimitiveWithInfer):
The type must be int32. Each value in the tensor should not greater than `max_time`.
Outputs:
- **loss** (Tensor) - A tensor containing log-probabilities, the shape is :math:`(batch_size)`. Has the same
- **loss** (Tensor) - A tensor containing log-probabilities, the shape is :math:`(batch_size)`, has the same
type with `inputs`.
- **gradient** (Tensor) - The gradient of `loss`. Has the same type and shape with `inputs`.
- **gradient** (Tensor) - The gradient of `loss`, has the same type and shape with `inputs`.
Examples:
>>> inputs = Tensor(np.random.random((2, 2, 3)), mindspore.float32)

22
mindspore/ops/operations/other_ops.py
View File

@ -32,7 +32,7 @@ class Assign(Primitive):
Inputs:
- **variable** (Parameter) - The `Parameter`.
- **value** (Tensor) - The value to assign.
- **value** (Tensor) - The value to be assigned.
Outputs:
Tensor, has the same type as original `variable`.
@ -75,7 +75,7 @@ class BoundingBoxEncode(PrimitiveWithInfer):
Args:
means (tuple): Means for encoding bounding boxes calculation. Default: (0.0, 0.0, 0.0, 0.0).
stds (tuple): Stds for encoding bounding boxes calculation. Default: (1.0, 1.0, 1.0, 1.0).
stds (tuple): The standard deviations of deltas calculation. Default: (1.0, 1.0, 1.0, 1.0).
Inputs:
- **anchor_box** (Tensor) - Anchor boxes. The shape of anchor_box must be (n, 4).
@ -131,8 +131,8 @@ class BoundingBoxDecode(PrimitiveWithInfer):
wh_ratio_clip (float): The limit of width and height ratio for decoding box calculation. Default: 0.016.
Inputs:
- **anchor_box** (Tensor) - Anchor boxes. The shape of anchor_box must be (n, 4).
- **deltas** (Tensor) - Delta of boxes. Which has the same shape with anchor_box.
- **anchor_box** (Tensor) - Anchor boxes. The shape of `anchor_box` must be (n, 4).
- **deltas** (Tensor) - Delta of boxes. Which has the same shape with `anchor_box`.
Outputs:
Tensor, decoded boxes.
@ -181,11 +181,11 @@ class CheckValid(PrimitiveWithInfer):
"""
Check bounding box.
Check whether the bounding box cross data and data border.
Check whether the bounding box cross data and data border are valid.
Inputs:
- **bboxes** (Tensor) - Bounding boxes tensor with shape (N, 4). Data type should be float16 or float32.
- **img_metas** (Tensor) - Raw image size information, format (height, width, ratio).
- **img_metas** (Tensor) - Raw image size information with the format of (height, width, ratio).
Data type should be float16 or float32.
Outputs:
@ -370,17 +370,17 @@ class Depend(Primitive):
class CheckBprop(PrimitiveWithInfer):
"""
Checks whether data type and shape of corresponding element from tuple x and y are the same.
Checks whether the data type and the shape of corresponding elements from tuples x and y are the same.
Raises:
TypeError: If not the same.
TypeError: If tuples x and y are not the same.
Inputs:
- **input_x** (tuple[Tensor]) - The input_x contains the outputs of bprop to be checked.
- **input_y** (tuple[Tensor]) - The input_y contains the inputs of bprop to check against.
- **input_x** (tuple[Tensor]) - The `input_x` contains the outputs of bprop to be checked.
- **input_y** (tuple[Tensor]) - The `input_y` contains the inputs of bprop to check against.
Outputs:
(tuple[Tensor]), the input_x,
(tuple[Tensor]), the `input_x`,
if data type and shape of corresponding elements from `input_x` and `input_y` are the same.
Examples: