Home Esplora Aiuto
Accedi
Prise3D
/
Thesis-NoiseDetection-CNN
2
0
Forka 0
File Problemi 0 Pull Requests 0 Wiki

Syntesis images noise detection using CNN approach

Albero (Tree): 67c2a0d3a5
Rami (Branch) Tag
Thesis-Noise...
ZIP TAR.GZ
jbuisine 67c2a0d3a5 Creation of modules for models 6 anni fa
img_train a22b32b71a First CNN model version 6 anni fa
img_validation a22b32b71a First CNN model version 6 anni fa
modules 67c2a0d3a5 Creation of modules for models 6 anni fa
.gitignore 67c2a0d3a5 Creation of modules for models 6 anni fa
README.md 67c2a0d3a5 Creation of modules for models 6 anni fa
RESULTS.md 2c8ad26c6b Add of model using SVD of images 6 anni fa
classification_cnn_keras.py 67c2a0d3a5 Creation of modules for models 6 anni fa
classification_cnn_keras_cross_validation.py 67c2a0d3a5 Creation of modules for models 6 anni fa
classification_cnn_keras_svd.py 67c2a0d3a5 Creation of modules for models 6 anni fa
generate_dataset.py 2c8ad26c6b Add of model using SVD of images 6 anni fa
requirements.txt 2c8ad26c6b Add of model using SVD of images 6 anni fa

README.md

Noise detection project

Requirements

pip install -r requirements.txt

How to use

Generate dataset (run only once time) :

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_SUB_IMAGES variables.

There are 3 kind of Neural Networks :

  • classification_cnn_keras.py : based croped on images
  • classification_cnn_keras_crossentropy.py : based croped on images which are randomly split for training
  • classification_cnn_keras_svd.py : based on svd metrics of image

Note that the image input size need to change in you used specific size for your croped images.

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

python classification_cnn_keras.py

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 grow during developement of the project

How to contribute

This git project uses git-flow implementation. You are free to contribute to it.