Description
Project description
MTMPLTool
一个基于 PyTorch Lightning 的机器学习模型训练和评估工具包。
简介
MTMPLTool 提供了一系列用于 PyTorch Lightning 机器学习项目的实用工具，包括：
- 自定义模型评估指标
- 基于 R2C（回归到分类）转换的专用损失函数
- 数据转换工具
- 学习率调度器
功能特性
评估指标
ExpectedLevelofError：使用绝对误差和相对误差阈值评估预测结果- 与 PyTorch Lightning 兼容的自定义指标
损失函数
BaseR2CLoss：R2C 转换损失函数的基类RegressionR2CLoss：带 R2C 转换的回归损失函数ClassificationR2CLoss：支持可选类别权重的交叉熵损失函数AttentionPoolingR2CLoss：带温度缩放的注意力池化损失函数
数据转换
ScalarToOnehot：将连续标量值转换为独热编码Random_0_or_1：用于随机值替换的数据增强工具
学习率调度器
LinearLRWarmupAndCosineAnnealingWarmRestarts：结合线性预热和余弦退火重启的学习率调度器
安装
pip install mtmpltool
环境要求
- Python >= 3.8
- PyTorch
- PyTorch Lightning
- pytorch-forecasting
开源协议
MIT 协议 - 详见 LICENSE 文件
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
No source distribution files available for this release.See tutorial on generating distribution archives.
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
mtmpltool-0.0.2-py3-none-any.whl
(18.1 kB
view details)
File details
Details for the file mtmpltool-0.0.2-py3-none-any.whl.
File metadata
- Download URL: mtmpltool-0.0.2-py3-none-any.whl
- Upload date:
- Size: 18.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
9c8561fbf2693747f21517d2da52b33eec29ce9d91b60b699c7315ef7c632e0c
|
|
| MD5 |
40bfe3f1f48f49ec48ee870ba239ea9f
|
|
| BLAKE2b-256 |
a1ff1e2bdda0cd79b446c49644eb6331f97213ae9c5da0f5dbcae172f980ec31
|
