Syntesis images noise detection using CNN approach

Jérôme BUISINE 238d151cfe Merge branch 'release/v0.1.1'		5 lat temu
modules	f4f4555442 3D CNN model added; Add of simulation curves for 2D and 3D models;	5 lat temu
.gitignore	7b3768132f Add of new reconstruction metric	5 lat temu
LICENSE	f80a4942e7 Creation of dataset file script added	5 lat temu
README.md	f4f4555442 3D CNN model added; Add of simulation curves for 2D and 3D models;	5 lat temu
display_simulation_curves.py	f4f4555442 3D CNN model added; Add of simulation curves for 2D and 3D models;	5 lat temu
generate_dataset.py	f4f4555442 3D CNN model added; Add of simulation curves for 2D and 3D models;	5 lat temu
generate_reconstructed_data.py	e88e2afb76 Add of prediction script; Add of simulation script	5 lat temu
predict_noisy_image.py	e88e2afb76 Add of prediction script; Add of simulation script	5 lat temu
predict_seuil_expe_curve.py	f4f4555442 3D CNN model added; Add of simulation curves for 2D and 3D models;	5 lat temu
requirements.txt	153ef98eae Update code with use of IPFML package	6 lat temu
run.sh	f4f4555442 3D CNN model added; Add of simulation curves for 2D and 3D models;	5 lat temu
run_maxwell_simulation_custom.sh	0d651ec858 Create generate dataset 3D	5 lat temu
train_model.py	f4f4555442 3D CNN model added; Add of simulation curves for 2D and 3D models;	5 lat temu
transformation_functions.py	e88e2afb76 Add of prediction script; Add of simulation script	5 lat temu

Noise detection project

Requirements

pip install -r requirements.txt

How to use

Generate reconstructed data from specific method of reconstruction (run only once time or clean data folder before):

python generate_reconstructed_data.py -h

Generate custom dataset from one reconstructed method or multiples (implemented later)

python generate_dataset.py -h

Reconstruction parameter (--params)

List of expected parameter by reconstruction method:

svd_reconstruction: Singular Values Decomposition
- Param definition: interval data used for reconstruction (begin, end)
- Example: "100, 200"
ipca_reconstruction: Iterative Principal Component Analysis
- Param definition: number of components used for compression and batch size
- Example: "30, 35"
fast_ica_reconstruction: Fast Iterative Component Analysis
- Param definition: number of components used for compression
- Example: "50"

Example:

python generate_dataset.py --output data/output_data_filename --metrics "svd_reconstruction, ipca_reconstruction, fast_ica_reconstruction" --renderer "maxwell" --scenes "A, D, G, H" --params "100, 200 :: 50, 10 :: 50" --nb_zones 10 --random 1

Then, train model using your custom dataset:

python train_model --data data/custom_dataset --output output_model_name

Modules

This project contains modules:

modules/utils/config.py: Store all configuration information about the project and dataset information
modules/utils/data.py: Usefull methods used for dataset
modules/models/metrics.py: Usefull methods for performance comparisons
modules/models/models.py: Generation of CNN model
modules/classes/Transformation.py: Transformation class for more easily manage computation

All these modules will be enhanced during development of the project

License

MIT

README.md