Home Verkennen Help
Inloggen
Prise3D
/
Thesis-NoiseDetection-26-attributes
2
0
Vork 0
Bestanden Issues 0 Pull-aanvragen 0 Wiki

Study of synthesis images noise detection using 26 attributes

Boom: c7f92ed4ef
Aftakkingen Labels
Thesis-Noise...
ZIP TAR.GZ
Jérôme BUISINE c7f92ed4ef Use of default svm metric 3 jaren geleden
OpenML_datasets f94ba1ea70 update openML datasets used 4 jaren geleden
analysis a18c913871 Update train surrogate model 3 jaren geleden
features_selection 48c4349333 sorted open ml problems in order to well restart 4 jaren geleden
generate c409191b1c update prediction script for new dataset structure 4 jaren geleden
modules @ cebf2adbf1 0a05939b74 Update of optimization process using backups 5 jaren geleden
optimization 75bfebb06b Remove add of surrogate model during local search 3 jaren geleden
prediction 21bd064e0f enable filter of attributes 3 jaren geleden
rnn @ 3e0abd40fe c863576804 New rnn submodule version 3 jaren geleden
utils 2fc4db3bfb use of wsao module for accelerate ILS (using surrogate) 4 jaren geleden
wsao @ a92ca5a285 c41293b6fa computation of mae and save it 4 jaren geleden
.gitignore 475f2851d1 Add of ocurences displayed 3 jaren geleden
.gitmodules 41659bc1c2 add of training using rnn models 4 jaren geleden
LICENSE dc0463b6b5 Project initialization 5 jaren geleden
README.md 30d257e0f7 update of the whole project to enable use of new dataset 4 jaren geleden
check_random_forest_perfomance.py 8dc3803465 update number of features as input 3 jaren geleden
check_random_forest_perfomance_rfe.py bc9d7037b7 Enable merge from rfe script 3 jaren geleden
custom_config.py e4f5839e36 Use surrogate from scract as proposed framework 4 jaren geleden
data_attributes.py a4119a186e update kolmogorov attributes 4 jaren geleden
find_best_attributes.py 6032efa1b1 Use of population for rendering surrogate 3 jaren geleden
find_best_attributes_from.py a2fb893050 svm can now be used for selector 4 jaren geleden
find_best_attributes_no_surrogate.py 4546ab0351 Lunch using no surrogate for comparisons 3 jaren geleden
find_best_attributes_surrogate.py 38ca51bff9 use of random forest 3 jaren geleden
find_best_attributes_surrogate_dl.py 6032efa1b1 Use of population for rendering surrogate 3 jaren geleden
find_best_attributes_surrogate_openML.py 6032efa1b1 Use of population for rendering surrogate 3 jaren geleden
find_best_attributes_surrogate_openML_multi.py 6032efa1b1 Use of population for rendering surrogate 3 jaren geleden
find_best_attributes_surrogate_openML_multi_specific.py 6032efa1b1 Use of population for rendering surrogate 3 jaren geleden
find_best_attributes_surrogate_svm.py c7f92ed4ef Use of default svm metric 3 jaren geleden
find_best_filters.py 6032efa1b1 Use of population for rendering surrogate 3 jaren geleden
models.py 0b94c18199 update number of parameters for svm 3 jaren geleden
requirements.txt c52c6fae6c now use of macop Python package for optimization process 4 jaren geleden
run_no_surrogate_rendering.sh 1e890c2840 Update bash script 3 jaren geleden
run_openML_surrogate.py 48c4349333 sorted open ml problems in order to well restart 4 jaren geleden
run_openML_surrogate_multi.py c41293b6fa computation of mae and save it 4 jaren geleden
run_openML_surrogate_multi_specific.py 33cf98b131 enable run of commands 4 jaren geleden
run_surrogate_rendering.sh b111f51621 Reduce pop size 3 jaren geleden
train_model.py c409191b1c update prediction script for new dataset structure 4 jaren geleden
train_model_attributes.py bc9d7037b7 Enable merge from rfe script 3 jaren geleden
train_model_filters.py b73b27ab44 add balanced data into SVC 4 jaren geleden

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