Science Score: 44.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (4.9%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: congningkaishi
- License: apache-2.0
- Language: Python
- Default Branch: master
- Size: 15.5 MB
Statistics
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
用于航拍图像小目标检测的跨层特征金字塔 Transformer
本仓库提供了CFPT的官方 PyTorch 实现。
在这篇论文中，提出了一种专为航拍图像小目标检测设计的跨层特征金字塔 Transformer。
下图展示了在 VisDrone-2019 DET 数据集上，基于 RetinaNet 的 CFPT 与其他特征金字塔网络的性能对比：
CFPT 的架构如下所示：
Weights
Due to the accidental deletion of the model weights prepared for this paper, we retrained the entire network, resulting in slight differences in performance metrics compared to the original study. Model | AP | Log | Link1 | Link2 | --- |:---:|:---:|:---:|:---: retinanetr18cfpt | 20.0 | Log | BaiduNetDisk | GoogleDrive retinanetr50cfpt | 22.4 | Log | BaiduNetDisk | GoogleDrive retinanetr101cfpt | 22.6 | Log | BaiduNetDisk | GoogleDrive
安装 我们的实验基于 torch 1.10+cu113、mmdet 2.24.1 和 mmcv-full 1.6.0。
有关 MMDetection 的基本使用方法，请参阅get_started.md。
1安装 PyTorch。
2安装 mmcv-full 和 MMDetection 工具箱。 pip install openmim mim install mmcv-full==1.6.0
3安装 albumentations 和其他包。 pip install einops pip install timm pip install yapf==0.40.1 pip install albumentations==1.1.0
4安装 albumentations 和其他包。 git clone https://github.com/duzw9311/CFPT.git cd ./CFPT pip install -e .
使用方法
数据准备
下载转换为 COCO 标注格式的 VisDrone2019-DET 数据集。您可以从这个链接下载。link.
训练
bash python tools/train.py configs/CFPT/retinanetr18cfpt1xvisdrone.py
测试
bash python tools/test.py configs/CFPT/retinanetr18cfpt1xvisdrone.py workdirs/retinanetr18cfpt1x_visdrone/latest.pth --eval bbox
Owner
- Login: congningkaishi
- Kind: user
- Repositories: 2
- Profile: https://github.com/congningkaishi
Citation (CITATION.cff)
cff-version: 1.2.0 message: "If you use this software, please cite it as below." authors: - name: "MMDetection Contributors" title: "OpenMMLab Detection Toolbox and Benchmark" date-released: 2018-08-22 url: "https://github.com/open-mmlab/mmdetection" license: Apache-2.0
GitHub Events
Total
- Push event: 1
- Create event: 2
Last Year
- Push event: 1
- Create event: 2
Dependencies
- pytorch/pytorch ${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel build
- pytorch/pytorch ${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel build
- albumentations >=0.3.2
- cython *
- numpy *
- docutils ==0.16.0
- myst-parser *
- sphinx ==4.0.2
- sphinx-copybutton *
- sphinx_markdown_tables *
- sphinx_rtd_theme ==0.5.2
- mmcv-full >=1.3.17
- cityscapesscripts *
- imagecorruptions *
- scipy *
- sklearn *
- timm *
- mmcv *
- torch *
- torchvision *
- matplotlib *
- numpy *
- pycocotools *
- six *
- terminaltables *
- asynctest * test
- codecov * test
- flake8 * test
- interrogate * test
- isort ==4.3.21 test
- kwarray * test
- onnx ==1.7.0 test
- onnxruntime >=1.8.0 test
- pytest * test
- ubelt * test
- xdoctest >=0.10.0 test
- yapf * test