Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/eric612/Mobilenet-YOLO-Pytorch
Include mobilenet series (v1,v2,v3...) and yolo series (yolov3,yolov4,...)
https://github.com/eric612/Mobilenet-YOLO-Pytorch
mobilenet-series mobilenet-yolo pytorch yolo-series yolov3
Last synced: 4 days ago
JSON representation
Include mobilenet series (v1,v2,v3...) and yolo series (yolov3,yolov4,...)
- Host: GitHub
- URL: https://github.com/eric612/Mobilenet-YOLO-Pytorch
- Owner: eric612
- License: mit
- Created: 2021-02-05T08:02:38.000Z (almost 4 years ago)
- Default Branch: main
- Last Pushed: 2021-12-29T06:20:29.000Z (almost 3 years ago)
- Last Synced: 2024-08-02T01:18:20.544Z (3 months ago)
- Topics: mobilenet-series, mobilenet-yolo, pytorch, yolo-series, yolov3
- Language: Python
- Homepage:
- Size: 1.08 MB
- Stars: 34
- Watchers: 2
- Forks: 12
- Open Issues: 3
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-yolo-object-detection - eric612/Mobilenet-YOLO-Pytorch - YOLO-Pytorch?style=social"/> : Include mobilenet series (v1,v2,v3...) and yolo series (yolov3,yolov4,...) . (Lighter and Deployment Frameworks)
- awesome-yolo-object-detection - eric612/Mobilenet-YOLO-Pytorch - YOLO-Pytorch?style=social"/> : Include mobilenet series (v1,v2,v3...) and yolo series (yolov3,yolov4,...) . (Lighter and Deployment Frameworks)
README
# Mobilenet-YOLO-Pytorch
## Model
A pytorch implementation of MobileNet-YOLO detection network , train on 07+12 , test on VOC2007 (imagenet pretrained , not coco)
Network|mAP|Resolution|download|
:---:|:---:|:---:|:---:|
MobileNetV2|72.1|352|[checkpoint](https://drive.google.com/drive/folders/11iNLZA5sOZP2tiTQB6pz6TAA2u5xyYCa?usp=sharing)|
## Training steps
1. Download dataset VOCdevkit/ , if already have , please skip this step
```
sh scripts/VOC2007.sh
sh scripts/VOC2012.sh
```
2. Create lmdb
```
sh scripts/create.sh
```
3. Start training
```
sh scripts/train.sh
```
## yolov3 training
see [branch](https://github.com/eric612/Mobilenet-YOLO-Pytorch/tree/yolov3)
## Hyper parameter optimization
```
nnictl create --config config.yml
```
## Demo
Download [checkpoint](https://drive.google.com/file/d/1eNIHaZGQHyb6WfOUmBuBU3K5urKFoL27/view?usp=sharing), and save at $Mobilenet-YOLO-Pytorch/checkpoints/bdd100k/model_best.pth.tar
```
sh scripts/inference.sh
```
## Under construction
- [ ] A new detector
- [x] yolov4
- [x] Multi-Task
- [x] Hyper Parameter Tuning
- [ ] Pruning
- [x] Porting KL720
## Acknowledgements
[AlexeyAB](https://github.com/AlexeyAB/darknet)
[diggerdu](https://github.com/diggerdu/Generalized-Intersection-over-Union)
[BobLiu20](https://github.com/BobLiu20/YOLOv3_PyTorch)
[bubbliiiing](https://github.com/bubbliiiing/yolov4-tiny-pytorch)
[aleju](https://github.com/aleju/imgaug)
[rmccorm4](https://github.com/rmccorm4/PyTorch-LMDB)
[hysts](https://github.com/hysts/pytorch_image_classification)
[utkuozbulak](https://github.com/utkuozbulak/pytorch-custom-dataset-examples)