From 59ab6d97201b68c9b87a051d34061051d7c680ad Mon Sep 17 00:00:00 2001 From: leilei_snow Date: Fri, 21 Aug 2020 10:28:16 +0800 Subject: [PATCH] modify grammar about tuple or list getitem with elements are nn.Cell --- .../constraints_on_network_construction.md | 41 ++++++++++++++++--- .../constraints_on_network_construction.md | 41 ++++++++++++++++--- 2 files changed, 70 insertions(+), 12 deletions(-) diff --git a/docs/source_en/constraints_on_network_construction.md b/docs/source_en/constraints_on_network_construction.md index 7c5de5bf72..0f0f35931d 100644 --- a/docs/source_en/constraints_on_network_construction.md +++ b/docs/source_en/constraints_on_network_construction.md @@ -93,7 +93,7 @@ | `**` |Scalar and `Tensor` | `//` |Scalar and `Tensor` | `%` |Scalar and `Tensor` -| `[]` |The operation object type can be `list`, `tuple`, or `Tensor`. Accessed multiple subscripts of lists and dictionaries can be used as r-values instead of l-values. Only when the operation object type is `tuple(nn.Cell)`, the index type can be Tensor. `tuple(nn.Cell)` means all elements type of tuple are `nn.Cell`. For details about access constraints for the tuple and Tensor types, see the description of slicing operations. +| `[]` |The operation object type can be `list`, `tuple`, or `Tensor`. Accessed multiple subscripts of lists and dictionaries can be used as r-values instead of l-values. Only when the operation object type is tuple or list with element type `nn.Cell`, the index type can be Tensor. For details about access constraints for the tuple and Tensor types, see the description of slicing operations. ### Index operation @@ -145,7 +145,7 @@ The index operation includes `tuple` and` Tensor`. The following focuses on the - Assignment: for example `tensor_x[..., ::, 1:] = u`. - Not supported in other situations -The slice value operations of the tuple type needs to focus on the slice value operation of the operation object type `tuple(nn.Cell)`. This operation is currently only supported by the GPU backend in Graph mode, and its syntax format is like `layers[index](*inputs)`, the example code is as follows: +The index value operation of tuple and list type, we need to focus on the index value operation of tuple or list whose element type is `nn.Cell`. This operation is currently only supported by the GPU backend in Graph mode, and its syntax format is like `layers[index](*inputs)`, the example code is as follows: ```python class Net(nn.Cell): def __init__(self): @@ -159,13 +159,42 @@ The slice value operations of the tuple type needs to focus on the slice value o return x ``` The grammar has the following constraints: -* Only supports slice value operation with operation object type `tuple(nn.Cell)`. -* The data type of the index value needs to be a Tensor scalar of type `int32`. -* The value range of index value is `[-n, n)`, where `n` is the size of the tuple, and the maximum supported tuple size is 1000. +* Only the index value operation of tuple or list whose element type is `nn.Cell` is supported. +* The index is a scalar `Tensor` of type `int32`, with a value range of `[-n, n)`, where `n` is the size of the tuple, and the maximum supported tuple size is 1000. * The number, type and shape of the input data of the `Construct` function of each Cell element in the tuple are the same, and the number of data output after the `Construct` function runs, the type and shape are also the same. * Each element in the tuple needs to be defined before the tuple is defined. +* This syntax does not support running branches as if, while, for and other control flow, except if the control condition of the control flow is constant. for example: + - Supported example: + ```python + class Net(nn.Cell): + def __init__(self, flag=True): + super(Net, self).__init__() + self.flag = flag + self.relu = nn.ReLU() + self.softmax = nn.Softmax() + self.layers = (self.relu, self.softmax) + + def construct(self, x, index): + if self.flag: + x = self.layers[index](x) + return x + ``` + - Unsupported example: + ```python + class Net(nn.Cell): + def __init__(self): + super(Net, self).__init__() + self.relu = nn.ReLU() + self.softmax = nn.Softmax() + self.layers = (self.relu, self.softmax) + + def construct(self, x, index, flag): + if flag: + x = self.layers[index](x) + return x + ``` -Other types of tuple also support slice value operations, but do not support index type as Tensor, support `tuple_x [start: stop: step]`, which has the same effect as Python, and will not be repeated here. +Tuple also support slice value operations, but do not support slice type as Tensor, support `tuple_x [start: stop: step]`, which has the same effect as Python, and will not be repeated here. ### Unsupported Syntax diff --git a/docs/source_zh_cn/constraints_on_network_construction.md b/docs/source_zh_cn/constraints_on_network_construction.md index 9e901d45e3..c858f57d2d 100644 --- a/docs/source_zh_cn/constraints_on_network_construction.md +++ b/docs/source_zh_cn/constraints_on_network_construction.md @@ -93,7 +93,7 @@ | `**` |标量、`Tensor` | `//` |标量、`Tensor` | `%` |标量、`Tensor` -| `[]` |操作对象类型支持`list`、`tuple`、`Tensor`，支持多重下标访问作为右值，但不支持多重下标访问作为左值，且索引类型仅当操作对象类型为`tuple(nn.Cell)`的取值操作时支持Tensor(这个操作目前Graph模式下仅GPU后端支持，其中`tuple(nn.Cell)`是指元素类型为nn.Cell的tuple类型)；Tuple、Tensor类型访问限制见切片操作中的说明。 +| `[]` |操作对象类型支持`list`、`tuple`、`Tensor`，支持多重下标访问作为右值，但不支持多重下标访问作为左值，且索引类型仅当操作对象类型为元素类型为`nn.Cell`的tuple或list的取值操作时支持Tensor(这个操作目前Graph模式下仅GPU后端支持)；Tuple、Tensor类型访问限制见切片操作中的说明。 ### 索引操作 @@ -144,7 +144,7 @@ - 赋值：例如`tensor_x[..., ::, 1:]=u` - 其他情况暂不支持 -tuple类型的切片取值操作，需要重点介绍一下操作对象类型为`tuple(nn.Cell)`的切片取值操作，该操作目前在Graph模式下仅GPU后端支持运行，其语法格式形如`layers[index](*inputs)`，具体示例代码如下： +tuple和list类型的索引取值操作，需要重点介绍一下元素类型为`nn.Cell`的tuple或list的索引取值操作，该操作目前在Graph模式下仅GPU后端支持运行，其语法格式形如`layers[index](*inputs)`，具体示例代码如下： ```python class Net(nn.Cell): def __init__(self): @@ -158,13 +158,42 @@ tuple类型的切片取值操作，需要重点介绍一下操作对象类型为 return x ``` 同时该语法有以下几个约束： -* 只支持操作对象类型为`tuple(nn.Cell)`的切片取值操作。 -* 索引值index的数据类型需要是`int32`类型的Tensor标量。 -* 索引值index的取值范围为`[-n, n)`, 其中`n`为tuple的size，支持的tuple的size的最大值为1000。 +* 只支持元素类型为`nn.Cell`的tuple或list的索引取值操作。 +* 索引值index的类型为`int32`的Tensor标量，取值范围为`[-n, n)`, 其中`n`为tuple的size，支持的tuple的size的最大值为1000。 * tuple中的每个Cell元素的Construct函数的输入数据的数目，类型和shape要求相同，且Construct函数运行后输出的数据的数目，类型和shape也要求相同。 * tuple中的每个Cell元素，需要在tuple定义之前完成定义。 +* 该语法不支持做为if、while、for等控制流的运行分支，如果控制流的控制条件为常量除外。举例说明： + - 支持的写法： + ```python + class Net(nn.Cell): + def __init__(self, flag=True): + super(Net, self).__init__() + self.flag = flag + self.relu = nn.ReLU() + self.softmax = nn.Softmax() + self.layers = (self.relu, self.softmax) + + def construct(self, x, index): + if self.flag: + x = self.layers[index](x) + return x + ``` + - 不支持的写法： + ```python + class Net(nn.Cell): + def __init__(self): + super(Net, self).__init__() + self.relu = nn.ReLU() + self.softmax = nn.Softmax() + self.layers = (self.relu, self.softmax) + + def construct(self, x, index, flag): + if flag: + x = self.layers[index](x) + return x + ``` -其它类型的tuple也支持切片取值操作, 但不支持索引类型为Tensor类型，支持`tuple_x[start:stop:step]`，其中操作对象为与Python的效果相同，这里不再赘述。 +tuple也支持切片取值操作, 但不支持切片类型为Tensor类型，支持`tuple_x[start:stop:step]`，其中操作对象为与Python的效果相同，这里不再赘述。 ### 不支持的语法 -- Gitee