mindspore.ops.DynamicGRUV2

class mindspore.ops.DynamicGRUV2(*args, **kwargs)[source]

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

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

where $h_{t}$ is the hidden state at time t, $x_{t}$ is the input at time t, $h_{(t - 1)}$ is the hidden state of the layer at time t-1 or the initial hidden state at time 0, and $r_{t}$ , $z_{t}$ , $n_{t}$ are the reset, update, and new gates, 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.
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.
init_h (Tensor) - Hidden state of initial time. Tensor of shape $(batch_size, hidden_size)$ . The data type must be float16 or float32.

Outputs:

y (Tensor) - A Tensor of shape :math: if num_proj > 0 (num_step, batch_size, min(hidden_size, num_proj), if num_proj == 0 (num_step, batch_size, hidden_size). 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 date type of init_h.
If bias_input is not None, bias_type is the date type of bias_input.
If bias_input is None and bias_hidden is not None, `bias_type is the date 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)