文档反馈

问题文档片段

问题文档片段包含公式时，显示为空格。

提交类型

issue

有点复杂...

找人问问吧。

请选择提交类型

问题类型

规范和低错类

- 规范和低错类：

- 错别字或拼写错误，标点符号使用错误、公式错误或显示异常。

- 链接错误、空单元格、格式错误。

- 英文中包含中文字符。

- 界面和描述不一致，但不影响操作。

- 表述不通顺，但不影响理解。

- 版本号不匹配：如软件包名称、界面版本号。

易用性

- 易用性：

- 关键步骤错误或缺失，无法指导用户完成任务。

- 缺少主要功能描述、关键词解释、必要前提条件、注意事项等。

- 描述内容存在歧义指代不明、上下文矛盾。

- 逻辑不清晰，该分类、分项、分步骤的没有给出。

正确性

- 正确性：

- 技术原理、功能、支持平台、参数类型、异常报错等描述和软件实现不一致。

- 原理图、架构图等存在错误。

- 命令、命令参数等错误。

- 代码片段错误。

- 命令无法完成对应功能。

- 界面错误，无法指导操作。

- 代码样例运行报错、运行结果不符。

风险提示

- 风险提示：

- 对重要数据或系统存在风险的操作，缺少安全提示。

内容合规

- 内容合规：

- 违反法律法规，涉及政治、领土主权等敏感词。

- 内容侵权。

请选择问题类型

问题描述

点击输入详细问题描述，以帮助我们快速定位问题。

文档反馈

mindspore.ops.DynamicGRUV2

class mindspore.ops.DynamicGRUV2(direction='UNIDIRECTIONAL', cell_depth=1, keep_prob=1.0, cell_clip=- 1.0, num_proj=0, time_major=True, activation='tanh', gate_order='rzh', reset_after=True, is_training=True)[source]

Applies a single-layer gated recurrent unit (GRU) to an input sequence.

\begin{array}{r} \begin{array}{ll} r_{t + 1} = σ (W_{i r} x_{t + 1} + b_{i r} + W_{h r} h_{(t)} + b_{h r}) \\ z_{t + 1} = σ (W_{i z} x_{t + 1} + b_{i z} + W_{h z} h_{(t)} + b_{h z}) \\ n_{t + 1} = \tanh (W_{i n} x_{t + 1} + b_{i n} + r_{t + 1} * (W_{h n} h_{(t)} + b_{h n})) \\ h_{t + 1} = (1 - z_{t + 1}) * n_{t + 1} + z_{t + 1} * h_{(t)} \end{array} \end{array}

where $h_{t + 1}$ is the hidden state at time t+1, $x_{t + 1}$ is the input at time t+1, $h_{t}$ is the hidden state of the layer at time t or the initial hidden state at time 0, and $r_{t + 1}$ , $z_{t + 1}$ , $n_{t + 1}$ are the reset, update, and new gates, respectively. $W$ , $b$ are the weight parameter and the deviation parameter respectively. $σ$ is the sigmoid function, and $*$ is the Hadamard product.

Parameters

direction (str) – A string identifying the direction in the op. Default: ‘UNIDIRECTIONAL’. Only ‘UNIDIRECTIONAL’ is currently supported.
cell_depth (int) – An integer identifying the cell depth in the op. Default: 1.
keep_prob (float) – A float identifying the keep prob in the op. Default: 1.0.
cell_clip (float) – A float identifying the cell clip in the op. Default: -1.0.
num_proj (int) – An integer identifying the num proj in the op. Default: 0.
time_major (bool) – A bool identifying the time major in the op. Default: True.
activation (str) – A string identifying the type of activation function in the op. Default: ‘tanh’. Only ‘tanh’ is currently supported.
gate_order (str) – A string identifying the gate order in weight and bias. Default: ‘rzh. ‘zrh’ is another option.
reset_after (bool) – A bool identifying whether to apply reset gate after matrix multiplication. Default: True.
is_training (bool) – A bool identifying is training in the op. Default: True.

Inputs:

x (Tensor) - Current words. Tensor of shape $(num_step, batch_size, input_size)$ . The data type must be float16.
weight_input (Tensor) - Input-hidden weight. Tensor of shape $(input_size, 3 \times hidden_size)$ . The data type must be float16.
weight_hidden (Tensor) - Hidden-hidden weight. Tensor of shape $(hidden_size, 3 \times hidden_size)$ . The data type must be float16.
init_h (Tensor) - Hidden state of initial time. Tensor of shape $(batch_size, hidden_size)$ . The data type must be float16 or float32.
bias_input (Tensor) - Input-hidden bias. Tensor of shape $(3 \times hidden_size)$ , or None. Has the same data type with input init_h.
bias_hidden (Tensor) - Hidden-hidden bias. Tensor of shape $(3 \times hidden_size)$ , or None. Has the same data type with input init_h.
seq_length (Tensor) - The length of each batch. Tensor of shape $(batch_size)$ . Only None is currently supported.

Outputs:

y (Tensor) - A Tensor of shape:
- y_shape = $(n u m_s t e p, b a t c h_s i z e, m i n (h i d d e n_s i z e, n u m_p r o j))$ : If num_proj > 0,
- y_shape = $(n u m_s t e p, b a t c h_s i z e, h i d d e n_s i z e)$ : If num_proj = 0.
Has the same data type with input bias_type.
output_h (Tensor) - A Tensor of shape $(num_step, batch_size, hidden_size)$ . Has the same data type with input bias_type.
update (Tensor) - A Tensor of shape $(num_step, batch_size, hidden_size)$ . Has the same data type with input bias_type.
reset (Tensor) - A Tensor of shape $(num_step, batch_size, hidden_size)$ . Has the same data type with input bias_type.
new (Tensor) - A Tensor of shape $(num_step, batch_size, hidden_size)$ . Has the same data type with input bias_type.
hidden_new (Tensor) - A Tensor of shape $(num_step, batch_size, hidden_size)$ . Has the same data type with input bias_type.

A note about the bias_type:

If bias_input and bias_hidden both are None, bias_type is data type of init_h.
If bias_input is not None, bias_type is the data type of bias_input.
If bias_input is None and bias_hidden is not None, bias_type is the data type of bias_hidden.

Raises

TypeError – If direction, activation or gate_order is not a str.
TypeError – If cell_depth or num_proj is not an int.
TypeError – If keep_prob or cell_clip is not a float.
TypeError – If time_major, reset_after or is_training is not a bool.
TypeError – If x, weight_input, weight_hidden, bias_input, bias_hidden, seq_length or ini_h is not a Tensor.
TypeError – If dtype of x, weight_input or weight_hidden is not float16.
TypeError – If dtype of init_h is neither float16 nor float32.

Supported Platforms:: Ascend

Examples

>>> x = Tensor(np.random.rand(2, 8, 64).astype(np.float16))
>>> weight_i = Tensor(np.random.rand(64, 48).astype(np.float16))
>>> weight_h = Tensor(np.random.rand(16, 48).astype(np.float16))
>>> bias_i = Tensor(np.random.rand(48).astype(np.float16))
>>> bias_h = Tensor(np.random.rand(48).astype(np.float16))
>>> init_h = Tensor(np.random.rand(8, 16).astype(np.float16))
>>> dynamic_gru_v2 = ops.DynamicGRUV2()
>>> output = dynamic_gru_v2(x, weight_i, weight_h, bias_i, bias_h, None, init_h)
>>> print(output[0].shape)
(2, 8, 16)