Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/BigDeviltjj/mxnet-detnet
unofficial reproduce of detnet
https://github.com/BigDeviltjj/mxnet-detnet
Last synced: 2 months ago
JSON representation
unofficial reproduce of detnet
- Host: GitHub
- URL: https://github.com/BigDeviltjj/mxnet-detnet
- Owner: BigDeviltjj
- Created: 2018-10-10T15:38:07.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2018-11-25T12:54:48.000Z (about 6 years ago)
- Last Synced: 2024-08-01T22:40:22.762Z (5 months ago)
- Language: Python
- Size: 5.61 MB
- Stars: 17
- Watchers: 3
- Forks: 2
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- Awesome-MXNet - detnet
README
# DetNet : A Backbone network for Object Detection
This repository tries to reproduce the result in [DetNet: A Backbone network for Object Detection](https://arxiv.org/pdf/1804.06215.pdf) using mxnet.
DetNet is evolved from fpn, thus one can change this repository to fpn easily.
### demo result
### set up environment
1.Clone this repository into the directory.
```
git clone git https://github.com/BigDeviltjj/mxnet-detnet.git
```
2.Download coco dataset into data directory.
3.Run`sh init.sh`.
4.You may need to install python modules including cv2, matplotlib and numpy etc.
## mAP
| Model | Training data | Test data | mAP |
|:-----------------:|:----------------:|:---------:|:----:|
| [detnet_coco-0016.params](https://drive.google.com/drive/folders/1Aon21uVFEsWTzDG2m1AMuo8ka-YZlRS3)(multi_scale)| train2017| val2017| 39.7|
### demo
Put the images you want to detect in images/, then run
```
python demo.py
```
detected images will be saved in det_images/
### train the model
You need to put the coco2017 dataset in data/ folder, and download pretrained model from [detnet59-0000.params](https://drive.google.com/drive/folders/1Aon21uVFEsWTzDG2m1AMuo8ka-YZlRS3). Then put them in folder model/pretrained_mode, then run
```
python train_end2end.py
```
### evaluate the model
Download the compressed trained model and symbol file [detnet_coco-0016.params](https://drive.google.com/drive/folders/1Aon21uVFEsWTzDG2m1AMuo8ka-YZlRS3) and unzip them then put them in folder output/detnet/coco/detnet/train2017/, then run
```
python test.py
```