2 Star 21 Fork 12

monkey_cici/mmdetection

加入 Gitee
与超过 1200万 开发者一起发现、参与优秀开源项目,私有仓库也完全免费 :)
免费加入
文件
.circleci
.dev_scripts
.github
configs
demo
docker
docs
mmdet
projects
AlignDETR
CO-DETR
ConvNeXt-V2
Detic
Detic_new
DiffusionDet
EfficientDet
configs
efficientdet
README.md
convert_tf_to_pt.py
HDINO
LabelStudio
RF100-Benchmark
SparseInst
VISION-Datasets
ViTDet
XDecoder
example_largemodel
example_project
gradio_demo
iSAID
requirements
resources
tests
tools
.gitignore
.owners.yml
.pre-commit-config-zh-cn.yaml
.pre-commit-config.yaml
.readthedocs.yml
CITATION.cff
LICENSE
MANIFEST.in
README.md
README_zh-CN.md
dataset-index.yml
model-index.yml
pytest.ini
requirements.txt
setup.cfg
setup.py
克隆/下载
贡献代码
同步代码
取消
提示: 由于 Git 不支持空文件夾,创建文件夹后会生成空的 .keep 文件
Loading...
README

EfficientDet

EfficientDet: Scalable and Efficient Object Detection, Mingxing Tan, Ruoming Pang, Quoc V. Le, CVPR 2020

Abstract

This is an implementation of EfficientDet based on MMDetection, MMCV, and MMEngine.
EfficientDet a new family of object detectors, which consistently achieve much better efficiency than prior art across a wide spectrum of resource constraints. In particular, with single model and single-scale, EfficientDet-D7 achieves stateof-the-art 55.1 AP on COCO test-dev with 77M parameters and 410B FLOP.
BiFPN is a simple yet highly effective weighted bi-directional feature pyramid network, which introduces learnable weights to learn the importance of different input features, while repeatedly applying topdown and bottom-up multi-scale feature fusion.
In contrast to other feature pyramid network, such as FPN, FPN + PAN, NAS-FPN, BiFPN achieves the best accuracy with fewer parameters and FLOPs.

Usage

Official TensorFlow Model

This project also supports official tensorflow model, it uses 90 categories and yxyx box encoding in training. If you want to use the original model weight to get official results, please refer to the following steps.

Model conversion

Firstly, download EfficientDet weights and unzip, please use the following command

tar -xzvf {EFFICIENTDET_WEIGHT}

Then, install tensorflow, please use the following command

pip install tensorflow-gpu==2.6.0

Lastly, convert weights from tensorflow to pytorch, please use the following command

python projects/EfficientDet/convert_tf_to_pt.py --backbone {BACKBONE_NAME} --tensorflow_weight {TENSORFLOW_WEIGHT_PATH} --out_weight {OUT_PATH}

Testing commands

In MMDetection's root directory, run the following command to test the model:

python tools/test.py projects/EfficientDet/configs/tensorflow/efficientdet_effb0_bifpn_8xb16-crop512-300e_coco_tf.py ${CHECKPOINT_PATH}

Reproduce Model

For convenience, we recommend the current implementation version, it uses 80 categories and xyxy encoding in training. On this basis, a higher result was finally achieved.

Training commands

In MMDetection's root directory, run the following command to train the model:

python tools/train.py projects/EfficientDet/configs/efficientdet_effb3_bifpn_8xb16-crop896-300e_coco.py

Testing commands

In MMDetection's root directory, run the following command to test the model:

python tools/test.py projects/EfficientDet/configs/efficientdet_effb3_bifpn_8xb16-crop896-300e_coco.py ${CHECKPOINT_PATH}

Results

Based on mmdetection, this project aligns the accuracy of the official model.

Method Backbone Pretrained Model Training set Test set Epoch Val Box AP Official AP Download
efficientdet-d0* efficientnet-b0 ImageNet COCO2017 Train COCO2017 Val 300 34.4 34.3
efficientdet-d3 efficientnet-b3 ImageNet COCO2017 Train COCO2017 Val 300 47.2 46.8 model | log

Note: *means use official tensorflow model weights to test.

Citation

@inproceedings{tan2020efficientdet,
  title={Efficientdet: Scalable and efficient object detection},
  author={Tan, Mingxing and Pang, Ruoming and Le, Quoc V},
  booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
  pages={10781--10790},
  year={2020}
}

Checklist

  • Milestone 1: PR-ready, and acceptable to be one of the projects/.

    • Finish the code

    • Basic docstrings & proper citation

    • Test-time correctness

    • A full README

  • Milestone 2: Indicates a successful model implementation.

    • Training-time correctness

  • Milestone 3: Good to be a part of our core package!

    • Type hints and docstrings

    • Unit tests

    • Code polishing

    • Metafile.yml

  • Move your modules into the core package following the codebase's file hierarchy structure.

  • Refactor your modules into the core package following the codebase's file hierarchy structure.

马建仓 AI 助手
尝试更多
代码解读
代码找茬
代码优化
Python
1
https://gitee.com/monkeycc/mmdetection.git
git@gitee.com:monkeycc/mmdetection.git
monkeycc
mmdetection
mmdetection
main

搜索帮助