Deep learning based denoising process

Reference

Yoon, Taekeun, et al. "Deep learning-based denoising for fast time-resolved flame emission spectroscopy in high-pressure combustion environment." Combustion and Flame 248 (2023): 112583. https://doi.org/10.1016/j.combustflame.2022.112583

Included folders and files

• data : raw dataset (download following file (url) 'rawdataM.mat' and locate in data folder)
• models : model strucutre python code
• utils : required functions
• main.py : main code
• enivornment.yaml : conda environment
• config.yaml : configuration

Requirements

• python environment (anaconda)
• python version 3.10.4
• window 10 64bit

Procedure

$ : command

1. Select working directory
2. Download data in ./data/
3. $ conda create -n DUCNN
4. $ conda activate DUCNN
5. $ conda env create --file environment.yaml
6. $ python main.py

Note1

If the GPU memory is not enough, Reduce batch_size