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.

PR

Just a small problem.

I can fix it online!

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

Differences with torch.nn.functional.gelu

torch.nn.functional.gelu

torch.nn.functional.gelu(input) -> Tensor

For more information, see torch.nn.functional.gelu.

mindspore.ops.gelu

mindspore.ops.gelu(input_x, approximate='none')

For more information, see mindspore.ops.gelu.

Differences

PyTorch: This function represents the Gaussian error linear unit function $GELU(X)=X\times \mathrm{\Phi }(x)$, where $\mathrm{\Phi }(x)$ is the cumulative distribution function of the Gaussian distribution. The input x denotes an arbitrary number of dimensions.

MindSpore: MindSpore API implements basically the same function as PyTorch.

Categories	Subcategories	PyTorch	MindSpore	Difference
Parameter	Parameter 1	-	approximate	There are two gelu approximation algorithms: ‘none’ and ‘tanh’, and the default value is ‘none’. After testing, the output is more similar to Pytorch when approximate is ‘none’.
Input	Single input	input	input_x	Same function, different parameter names

Code Example 1

The two APIs achieve the same function and have the same usage.

# PyTorch
import torch
input = torch.Tensor([[2, 4], [1, 2]])
output = torch.nn.functional.gelu(input)
print(output.detach().numpy())
# [[1.9544997 3.9998734]
#  [0.8413447 1.9544997]]

# MindSpore
import mindspore
import numpy as np
x = mindspore.Tensor(np.array([[2, 4], [1, 2]]), mindspore.float32)
output = mindspore.ops.gelu(x)
print(output)
# [[1.9545997 3.99993]
#  [0.841192 1.9545977]]