surMSE
A loss function @PyTorch, that allows the target to be exceeded in the target direction.
思路说明
允许输入与目标方向相同,但模长比目标大.此时损失为零.
因为神经网络经常表现出输出稍微不达目标的特性,通过减弱使输出接近零的梯度,尝试缓解这个问题.
Install
pip install surMSE
Use
from surMSE import surMSE
...
loss=surMSE(input,target,dim=None,scale=True,eps=1e-8,meanOut=True,haveBatch=True,protect=None)
dim表示在哪些维度上计算损失,一般开启除Batch维之外的全部维度.设定为None则自动计算.
dim=None,haveBatch=True时,自动排除首维.dim=None,haveBatch=False时在全部维度上计算.
scale控制是否根据target模长控制对应样本损失的增益,如果开启,将通过target模长给损失加权;如果关闭,在一半空间上将等效于MSE.
meanOut控制是否在返回前使用平均的方法合并"dim"参数指定外的剩余维度.如果不开启,取决于数据维度和dim设置,返回的tensor将不一定只有一个元素.
protect柔性防止损失值超越protect值的样本对总损失造成过大影响.设置为0关闭此功能,设置为None自动设置当前批次损失值的平均值作为protect值.
1 maintainer
Metadata
1 maintainer
Release files for surMSE 0.0.3
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| surmse-0.0.3.tar.gz | 8.1 kB | With provenance | Details for surmse-0.0.3.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| surmse-0.0.3-py3-none-any.whl | Python 3 | none | any | Details for surmse-0.0.3-py3-none-any.whl |
Total release size: 16.5 kB
Release files / surmse-0.0.3.tar.gz
| Download URL | surmse-0.0.3.tar.gz |
|---|---|
| Size | 8.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
9d6c5d41a116604c03a33e954fe85b727da0bd13ba73c096cc8fc01a27658d37
|
|
BLAKE2b-256 checksum How to use checksums |
d4c886436fefd470c8f0b807e3074effbd72e57936319953e5fd601d6a8024d9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 9, 2026.
Transparency logRelease files / surmse-0.0.3-py3-none-any.whl
| Download URL | surmse-0.0.3-py3-none-any.whl |
|---|---|
| Size | 8.3 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
40452471f203c989c5e09a7cf3fa83dacf94547dc02e34600db6d19e9469cca2
|
|
BLAKE2b-256 checksum How to use checksums |
967a70cc258329735bd6bac3a59a8c3edfa9441bb23eedabb0c39a4c09e253b3
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 9, 2026.
Transparency logSecurity for surMSE 0.0.3
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
Both files in this release have been uploaded with provenance metadata.
Attestation for surmse-0.0.3.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jul 9, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
