# A_Reinforcement_Learning_Paradigm_of_Configuring_Visual_Enhancement_for_Object_Detection_in_Underwater_Scenes

**Repository Path**: wanghaoupc/RL_Configuring_VisualEnhancment_for_ObjectDetection

## Basic Information

- **Project Name**: A_Reinforcement_Learning_Paradigm_of_Configuring_Visual_Enhancement_for_Object_Detection_in_Underwater_Scenes
- **Description**: RL_Configuring_VisualEnhancment_for_ObjectDetection
- **Primary Language**: Python
- **License**: MIT
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 3
- **Forks**: 1
- **Created**: 2021-08-10
- **Last Updated**: 2023-08-24

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# A Reinforcement Learning Paradigm of Configuring Visual Enhancement for Object Detection in Underwater Scenes


#### Prerequisites
1. Python 3.7
2. CUDA 10.2

#### Compilation
Install all the python dependencies using pip:
        
        pip install -r requirements.txt

#### Data Preparation
Prepare the dataset according to https://blog.csdn.net/weixin_48994268/article/details/115282688 and put the data into the corresponding folder as follows:
   
        RLVEOD
        ├── data
        │   ├── images
        │   │   ├── train
        │   │   ├── test
        │   │   └── demo
        │   ├── labels
        │   │   ├── train (1)
        │   │   └── test  (2)
        │   └── ImageSets
        │       ├── train.txt
        │       ├── test.txt
        │       └── demo.txt
        └── RL
            └── img
                ├── train
                │   └── labels
                │       └── test (Same as (1))
                └── test
                    └── labels
                        └── test (Same as (2))

#### Model Preparation
Prepare the YOLOv5s well-trained object detector by https://github.com/ultralytics/yolov5 and put it into:
        
        ./RLVEOD/RL/yolov5s/weights/

#### Train
        
        CUDA_VISIBLE_DEVICES=$GPU_ID python main

#### Test (Change the default value of --test to True and the default value of --model_path to $model path in ./checkpoints)
        
        CUDA_VISIBLE_DEVICES=$GPU_ID python main

#### Demo (Change the default value of --demo to True and the default value of --model_path to $model path in ./checkpoints) 
        
        CUDA_VISIBLE_DEVICES=$GPU_ID python main