https://github.com/luogen1996/OneTeacher

https://github.com/luogen1996/OneTeacher

Last synced: 3 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/luogen1996/OneTeacher
• Owner: luogen1996
• License: gpl-3.0
• Created: 2023-01-29T14:34:05.000Z (about 2 years ago)
• Default Branch: main
• Last Pushed: 2023-02-12T05:35:30.000Z (about 2 years ago)
• Last Synced: 2024-11-06T19:07:12.789Z (4 months ago)
• Language: Python
• Size: 2.22 MB
• Stars: 79
• Watchers: 1
• Forks: 9
• Open Issues: 12
• Metadata Files:
  • Readme: README.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-yolo-object-detection - OneTeacher - to-end Semi-supervised Learning for One-stage Object Detection". (**[arXiv 2023](https://arxiv.org/abs/2302.11299)**). (Applications)
• awesome-yolo-object-detection - OneTeacher - to-end Semi-supervised Learning for One-stage Object Detection". (**[arXiv 2023](https://arxiv.org/abs/2302.11299)**). (Applications)

README

        
# OneTeacher

Official implementation of  "Towards End-to-end Semi-supervised Learning for One-stage Object Detection".

OneTeacher is a semi-supervised framework for YOLOV5, which is equiped with two novel designs, namely Multi-view Pseudo-label Refinement and Decoupled Semi-supervised Optimization.



	



## Updates 

- (2023/1/29) Release our  project.

## Data Preparation

1. Prepare the datasets of COCO and VOC, please refer to [YOLOv5](./README_YOLOV5.md)

After that, the file structure should look like:

```

   |-- OneTeacher

   |-- datasets

       |-- coco

             |-- images

                  |-- train2017

                  |-- val2017

                  |-- test2017

             |-- labels

             |-- annotations

                  |-- instances_train2017.json

                  |-- instances_val2017.json

```

2. Generate semi-supervised data split.

```

python active_sampling/generate_random_supervised_seed_yolo.py  --dataset_name 'coco_2017_train'  --random_seeds 0,1,2,3,4,5,6,7,8,9  --random_file  ./data_processing/COCO_supervision.txt   --random_percent 10.0  --output_file ./dataseed/COCO_supervision_10.json

```

## Training and Evaluation

Semi-supervised Learning on COCO 10%

```sh 

bash script/coco_semi_script.sh 32 2 0,1

``` 

Semi-supervised Learning on VOC 25%

```sh 

bash script/voc_semi_script.sh 32 2 0,1

``` 

Fully-supervised Learning on COCO 10%

```sh 

bash script/coco_fully_script.sh 32 2 0,1

``` 

Fully-supervised Learning on VOC 25%

```sh 

bash script/voc_fully_script.sh 32 2 0,1

```