Startseite Erkunden Hilfe
Anmelden
Prise3D
/
Thesis-NoiseDetection-CNN
2
0
Fork 0
Dateien Issues 0 Pull-Requests 0 Wiki

Syntesis images noise detection using CNN approach

Struktur: 8bd0bd342b
Branches Tags
Thesis-Noise...
ZIP TAR.GZ
Jérôme BUISINE 8bd0bd342b Add of CNN model and run script vor 5 Jahren
modules f80a4942e7 Creation of dataset file script added vor 5 Jahren
.gitignore f80a4942e7 Creation of dataset file script added vor 5 Jahren
LICENSE f80a4942e7 Creation of dataset file script added vor 5 Jahren
README.md 0c40621cc5 Update of documentation vor 5 Jahren
RESULTS.md 2c8ad26c6b Add of model using SVD of images vor 6 Jahren
TODO.md f80a4942e7 Creation of dataset file script added vor 5 Jahren
generate_dataset.py 8bd0bd342b Add of CNN model and run script vor 5 Jahren
generate_reconstructed_data.py f80a4942e7 Creation of dataset file script added vor 5 Jahren
preprocessing_functions.py f80a4942e7 Creation of dataset file script added vor 5 Jahren
requirements.txt 153ef98eae Update code with use of IPFML package vor 6 Jahren
run.sh 8bd0bd342b Add of CNN model and run script vor 5 Jahren
train_model.py 8bd0bd342b Add of CNN model and run script vor 5 Jahren

README.md

Noise detection project

Requirements

pip install -r requirements.txt

How to use

Generate dataset (run only once time or clean data folder before):

python generate_dataset.py

It will split scenes and generate all data you need for your neural network. You can specify the number of sub images you want in the script by modifying _NUMBER_SUBIMAGES variable or using parameter.

python generate_dataset.py --nb xxxx

There are 3 kinds of Neural Networks:

  • classification_cnn_keras.py: based on cropped images and do convolution
  • classification_cnn_keras_cross_validation.py: based on cropped images and do convolution. Data are randomly split for training
  • classification_cnn_keras_svd.py: based on svd metrics of image

After your built your neural network in classification_cnn_keras.py, you just have to run it:

python classification_cnn_keras_svd.py --directory xxxx --output xxxxx --batch_size xx --epochs xx --img xx (or --image_width xx --img_height xx)

A config file in json is available and keeps in memory all image sizes available.

Modules

This project contains modules:

  • modules/image_metrics: where all computed metrics function are developed
  • modules/model_helper: contains helpful function to save or display model information and performance

All these modules will be enhanced during development of the project

License

MIT