Document feedback

Question document fragment

When a question document fragment contains a formula, it is displayed as a space.

Submission type

issue

It's a little complicated...

I'd like to ask someone.

Please select the submission type

Problem type

Specifications and Common Mistakes

- Specifications and Common Mistakes:

- Misspellings or punctuation mistakes,incorrect formulas, abnormal display.

- Incorrect links, empty cells, or wrong formats.

- Chinese characters in English context.

- Minor inconsistencies between the UI and descriptions.

- Low writing fluency that does not affect understanding.

- Incorrect version numbers, including software package names and version numbers on the UI.

Usability

- Usability:

- Incorrect or missing key steps.

- Missing main function descriptions, keyword explanation, necessary prerequisites, or precautions.

- Ambiguous descriptions, unclear reference, or contradictory context.

- Unclear logic, such as missing classifications, items, and steps.

Correctness

- Correctness:

- Technical principles, function descriptions, supported platforms, parameter types, or exceptions inconsistent with that of software implementation.

- Incorrect schematic or architecture diagrams.

- Incorrect commands or command parameters.

- Incorrect code.

- Commands inconsistent with the functions.

- Wrong screenshots.

- Sample code running error, or running results inconsistent with the expectation.

Risk Warnings

- Risk Warnings:

- Lack of risk warnings for operations that may damage the system or important data.

Content Compliance

- Content Compliance:

- Contents that may violate applicable laws and regulations or geo-cultural context-sensitive words and expressions.

- Copyright infringement.

Please select the type of question

Problem description

Describe the bug so that we can quickly locate the problem.

Submit

Document feedback

mindspore.nn.TransformerEncoderLayer

class mindspore.nn.TransformerEncoderLayer(d_model: int, nhead: int, dim_feedforward: int = 2048, dropout: float = 0.1, activation: Union[str, Cell, callable] = 'relu', layer_norm_eps: float = 1e-05, batch_first: bool = False, norm_first: bool = False)

Transformer Encoder Layer. This is an implementation of the single layer of the transformer encoder layer, including multihead attention and feedward layer.

Warning

This is an experimental API that is subject to change or deletion.

Parameters

• d_model (int) – The number of features in the input tensor.

• nhead (int) – The number of heads in the MultiheadAttention modules.

• dim_feedforward (int) – The dimension of the feedforward layer. Default: 2048.

• dropout (float) – The dropout value. Default: 0.1.

• activation (Union[str, callable, Cell]) – The activation function of the intermediate layer, can be a string ("relu" or "gelu"), Cell instance (nn.ReLU() or nn.GELU()) or a callable (ops.relu or ops.gelu). Default: "relu".

• layer_norm_eps (float) – The epsilon value in LayerNorm modules. Default: 1e-5.

• batch_first (bool) – If batch_first = True, then the shape of input and output tensors is $(batch,seq,feature)$ , otherwise the shape is $(seq,batch,feature)$ . Default: False.

• norm_first (bool) – If norm_first = True, layer norm is done prior to attention and feedforward operations, respectively. Default: False.

Inputs:

• src (Tensor): the sequence to the encoder layer.

• src_mask (Tensor, optional): the mask for the src sequence. Default: None.

• src_key_padding_mask (Tensor, optional): the mask for the src keys per batch. Default: None.

Outputs:

Tensor.

Raises

• ValueError – If the init argument activation is not str, callable or Cell instance.

• ValueError – If the init argument activation is not mindspore.nn.ReLU, mindspore.nn.GELU instance, mindspore.ops.relu(), mindspore.ops.gelu() instance, “relu” or “gelu” .

Supported Platforms:

Ascend GPU CPU

Examples

>>> import mindspore as ms
>>> import numpy as np
>>> encoder_layer = ms.nn.TransformerEncoderLayer(d_model=512, nhead=8)
>>> src = ms.Tensor(np.random.rand(10, 32, 512), ms.float32)
>>> out = encoder_layer(src)
>>> # Alternatively, when batch_first=True:
>>> encoder_layer = ms.nn.TransformerEncoderLayer(d_model=512, nhead=8, batch_first=True)
>>> src = ms.Tensor(np.random.rand(32, 10, 512), ms.float32)
>>> out = encoder_layer(src)
>>> print(out.shape)
(32, 10, 512)