# EfficientDet: Scalable and Efficient Object Detection
## Introduction
Here is our pytorch implementation of the model described in the paper **EfficientDet: Scalable and Efficient Object Detection** [paper](https://arxiv.org/abs/1911.09070) (*Note*: We also provide pre-trained weights, which you could see at ./trained_models)
<p align="center">
<img src="demo/video.gif"><br/>
<i>An example of our model's output.</i>
</p>
## Datasets
| Dataset | Classes | #Train images | #Validation images |
|------------------------|:---------:|:-----------------------:|:----------------------------:|
| COCO2017 | 80 | 118k | 5k |
Create a data folder under the repository,
```
cd {repo_root}
mkdir data
```
- **COCO**:
Download the coco images and annotations from [coco website](http://cocodataset.org/#download). Make sure to put the files as the following structure:
```
COCO
├── annotations
│ ├── instances_train2017.json
│ └── instances_val2017.json
│── images
├── train2017
└── val2017
```
## How to use our code
With our code, you can:
* **Train your model** by running **python train.py**
* **Evaluate mAP for COCO dataset** by running **python mAP_evaluation.py**
* **Test your model for COCO dataset** by running **python test_dataset.py --pretrained_model path/to/trained_model**
* **Test your model for video** by running **python test_video.py --pretrained_model path/to/trained_model --input path/to/input/file --output path/to/output/file**
## Experiments
We trained our model by using 3 NVIDIA GTX 1080Ti. Below is mAP (mean average precision) for COCO val2017 dataset
| Average Precision | IoU=0.50:0.95 | area= all | maxDets=100 | 0.314 |
|-----------------------|:-------------------:|:-----------------:|:-----------------:|:-------------:|
| Average Precision | IoU=0.50 | area= all | maxDets=100 | 0.461 |
| Average Precision | IoU=0.75 | area= all | maxDets=100 | 0.343 |
| Average Precision | IoU=0.50:0.95 | area= small | maxDets=100 | 0.093 |
| Average Precision | IoU=0.50:0.95 | area= medium | maxDets=100 | 0.358 |
| Average Precision | IoU=0.50:0.95 | area= large | maxDets=100 | 0.517 |
| Average Recall | IoU=0.50:0.95 | area= all | maxDets=1 | 0.268 |
| Average Recall | IoU=0.50:0.95 | area= all | maxDets=10 | 0.382 |
| Average Recall | IoU=0.50:0.95 | area= all | maxDets=100 | 0.403 |
| Average Recall | IoU=0.50:0.95 | area= small | maxDets=100 | 0.117 |
| Average Recall | IoU=0.50:0.95 | area= medium | maxDets=100 | 0.486 |
| Average Recall | IoU=0.50:0.95 | area= large | maxDets=100 | 0.625 |
## Results
Some predictions are shown below:
<img src="demo/1.jpg" width="280"> <img src="demo/2.jpg" width="280"> <img src="demo/3.jpg" width="280">
<img src="demo/4.jpg" width="280"> <img src="demo/5.jpg" width="280"> <img src="demo/6.jpg" width="280">
<img src="demo/7.jpg" width="280"> <img src="demo/8.jpg" width="280"> <img src="demo/9.jpg" width="280">
## Requirements
* **python 3.6**
* **pytorch 1.2**
* **opencv (cv2)**
* **tensorboard**
* **tensorboardX** (This library could be skipped if you do not use SummaryWriter)
* **pycocotools**
* **efficientnet_pytorch**
## References
- Mingxing Tan, Ruoming Pang, Quoc V. Le. "EfficientDet: Scalable and Efficient Object Detection." [EfficientDet](https://arxiv.org/abs/1911.09070).
- Our implementation borrows some parts from [RetinaNet.Pytorch](https://github.com/yhenon/pytorch-retinanet)
## Citation
@article{EfficientDetSignatrix,
Author = {Signatrix GmbH},
Title = {A Pytorch Implementation of EfficientDet Object Detection},
Journal = {https://github.com/signatrix/efficientdet},
Year = {2020}
}
没有合适的资源?快使用搜索试试~ 我知道了~
资源推荐
资源详情
资源评论
收起资源包目录
_Pretrained_weights_provided__EfficientDet__Scalab_efficientdet-1.zip (25个子文件)
DataXujing-efficientdet-1-f5325d3
src
utils.py 5KB
loss.py 6KB
dataset.py 6KB
model.py 12KB
config.py 3KB
LICENSE 1KB
demo
2.jpg 80KB
6.jpg 127KB
1.jpg 235KB
5.jpg 121KB
8.jpg 208KB
3.jpg 83KB
video.gif 10.66MB
7.jpg 132KB
9.jpg 86KB
4.jpg 150KB
test_dataset.py 3KB
trained_models
signatrix_efficientdet_coco.pth 17.53MB
signatrix_efficientdet_coco.onnx 17.38MB
requirements.txt 45B
.gitignore 1KB
train.py 8KB
test_video.py 3KB
README.md 4KB
mAP_evaluation.py 2KB
共 25 条
- 1
资源评论
普通网友
- 粉丝: 0
- 资源: 510
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
最新资源
- 分享Java相关的东西 - Java安全漫谈笔记相关内容.zip
- 具有适合 Java 应用程序的顺序定义的 Cloud Native Buildpack.zip
- 网络建设运维资料库职业
- 关于 Java 的一切.zip
- 爬虫安装 XPath Helper 2.0
- 使用特定版本的 Java 设置 GitHub Actions 工作流程.zip
- 使用 Winwheel.js 在 HTML 画布上创建旋转奖品轮.zip
- 使用 Java 编译器 API 的 Java 语言服务器.zip
- 使用 Java 的无逻辑和语义 Mustache 模板.zip
- 使用 Java EE 7 的 Java Petstore.zip
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功