A custom SPDConv + WTConv module for YOLO models
Project description
SPDConv
This is a custom SPDConv module for YOLO models, designed to improve performance on specific tasks. 一种新的卷积神经网络构建SPD-Conv,旨在解决低分辨率或小目标任务中的性能下降问题。通过替换步幅卷积和池化层,SPD-Conv保持了细粒度信息,提高了特征学习效率
WTConv
This is a custom WTConv module for YOLO models, designed to improve performance on specific tasks. 引入了小波卷积模块,旨在扩大卷积的感受野并有效捕捉图像中的低频信息。其对多尺度问题和小目标问题上有很好的效果
H-RAMI
This is a custom WTConv module for YOLO models H-RAMi将不同层级的信息结合在一起,形成最终的输出。这一过程能够利用不同层次间的信息交互,得到更加全面且具有层次感的理解
Installation
You can install the SPDConv module via pip:
pip install xl_yolo_pkg
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
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
File details
Details for the file xl_yolo_pkg-0.1.3.tar.gz.
File metadata
- Download URL: xl_yolo_pkg-0.1.3.tar.gz
- Upload date:
- Size: 42.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.0.1 CPython/3.8.20
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
34537dd5dfd5051e2cd7e63524e3c4a464faa86f966f489361a910ef2e86a401
|
|
| MD5 |
f8e4aa00cb769baa8ecaec762a8e4817
|
|
| BLAKE2b-256 |
bac3d84367a7ffe99a85e18d45e75ab8bf5ab74855de673e37c9aa71277c9534
|
File details
Details for the file xl_yolo_pkg-0.1.3-py3-none-any.whl.
File metadata
- Download URL: xl_yolo_pkg-0.1.3-py3-none-any.whl
- Upload date:
- Size: 46.3 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.0.1 CPython/3.8.20
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
6f08e5c26702627ce117c8bf870a6c0e433926294d9743970fbab2196eb15eab
|
|
| MD5 |
e8b5cb9ae3b8021118f7da1eb0db008b
|
|
| BLAKE2b-256 |
da2f17eb44358b3158ebb9e0e4f5628049394acf9fb91f4ecdf64e020221ff8c
|