Study of synthesis images noise detection using 26 attributes

Jérôme BUISINE a18c913871 Update train surrogate model 3 years ago
OpenML_datasets f94ba1ea70 update openML datasets used 3 years ago
analysis a18c913871 Update train surrogate model 3 years ago
features_selection 48c4349333 sorted open ml problems in order to well restart 3 years ago
generate c409191b1c update prediction script for new dataset structure 4 years ago
modules @ cebf2adbf1 0a05939b74 Update of optimization process using backups 5 years ago
optimization 75bfebb06b Remove add of surrogate model during local search 3 years ago
prediction c409191b1c update prediction script for new dataset structure 4 years ago
rnn @ 8c2fc8888c 427d117327 Update use of surrogate 3 years ago
utils 2fc4db3bfb use of wsao module for accelerate ILS (using surrogate) 4 years ago
wsao @ a92ca5a285 c41293b6fa computation of mae and save it 3 years ago
.gitignore 475f2851d1 Add of ocurences displayed 3 years ago
.gitmodules 41659bc1c2 add of training using rnn models 4 years ago
LICENSE dc0463b6b5 Project initialization 5 years ago
README.md 30d257e0f7 update of the whole project to enable use of new dataset 4 years ago
check_random_forest_perfomance.py 8dc3803465 update number of features as input 3 years ago
check_random_forest_perfomance_rfe.py 7cc4631e5d Add test of RFE performances and n_jobs 3 years ago
custom_config.py e4f5839e36 Use surrogate from scract as proposed framework 4 years ago
data_attributes.py a4119a186e update kolmogorov attributes 4 years ago
find_best_attributes.py 6032efa1b1 Use of population for rendering surrogate 3 years ago
find_best_attributes_from.py a2fb893050 svm can now be used for selector 4 years ago
find_best_attributes_no_surrogate.py 4546ab0351 Lunch using no surrogate for comparisons 3 years ago
find_best_attributes_surrogate.py 38ca51bff9 use of random forest 3 years ago
find_best_attributes_surrogate_dl.py 6032efa1b1 Use of population for rendering surrogate 3 years ago
find_best_attributes_surrogate_openML.py 6032efa1b1 Use of population for rendering surrogate 3 years ago
find_best_attributes_surrogate_openML_multi.py 6032efa1b1 Use of population for rendering surrogate 3 years ago
find_best_attributes_surrogate_openML_multi_specific.py 6032efa1b1 Use of population for rendering surrogate 3 years ago
find_best_filters.py 6032efa1b1 Use of population for rendering surrogate 3 years ago
models.py 62af7d2a9e Update CV parameter when training 3 years ago
requirements.txt c52c6fae6c now use of macop Python package for optimization process 4 years ago
run_no_surrogate_rendering.sh 1e890c2840 Update bash script 3 years ago
run_openML_surrogate.py 48c4349333 sorted open ml problems in order to well restart 3 years ago
run_openML_surrogate_multi.py c41293b6fa computation of mae and save it 3 years ago
run_openML_surrogate_multi_specific.py 33cf98b131 enable run of commands 3 years ago
run_surrogate_rendering.sh b111f51621 Reduce pop size 3 years ago
train_model.py c409191b1c update prediction script for new dataset structure 4 years ago
train_model_attributes.py a18c913871 Update train surrogate model 3 years ago
train_model_filters.py b73b27ab44 add balanced data into SVC 4 years ago

README.md

Noise detection using 26 attributes

Description

Noise detection on synthesis images with 26 attributes obtained using few filters.

Filters list:

  • average
  • wiener
  • median
  • gaussian
  • wavelet

Requirements

pip install -r requirements.txt

Project structure

Link to your dataset

You need database which respects this structure:

  • dataset/
    • Scene1/
    • Scene1_00050.png
    • Scene1_00070.png
    • ...
    • Scene1_01180.png
    • Scene1_01200.png
    • Scene2/
    • ...
    • ...

Code architecture description

  • modules/*: contains all modules usefull for the whole project (such as configuration variables)
  • analysis/*: contains all jupyter notebook used for analysis during thesis
  • generate/*: contains python scripts for generate data from scenes (described later)
  • data_processing/*: all python scripts for generate custom dataset for models
  • prediction/*: all python scripts for predict new threshold from computed models
  • data_attributes.py: files which contains all extracted features implementation from an image.
  • custom_config.py: override the main configuration project of modules/config/global_config.py
  • train_model.py: script which is used to run specific model available.

Generated data directories:

  • data/*: folder which will contain all generated .train & .test files in order to train model.
  • data/saved_models/*: all scikit learn or keras models saved.
  • data/models_info/*: all markdown files generated to get quick information about model performance and prediction obtained after running run/runAll_*.sh script.
  • data/results/: This folder contains model_comparisons.csv file used for store models performance.

License

The MIT license