Skip to content

image processing task I did using fine-tuning, DCNNs and common data augmentation techniques. dataset consisted of 1600 x-ray images of human stomach which included 800 each of pylori(helicobacter) positive and negative. augmented the dataset using common data augmentation techniques.

Notifications You must be signed in to change notification settings

sukhbat112/pylori-detection-DCNN

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

pylori-detection-DCNN

uses the following libraries efficiently: tensorflow.keras, matplotlib, sklearn, pandas.

init_model.py initializes each CNN models with respective hyper parameters.

train.py trains the fully connected part of DCNN, also changing the architecture of FC layer is possible.

CNN change is also possible.

train.py prints the training process and outputs it into 'history.csv' using pandas and saves the parameters in .h5 file.

also train.py calculates and plots the ROC curve (receiver operating characteristic curve) of the trained models.

mobnet plot.py and densnet plot.py both plots the accuracy and loss curve for both training and validation(evaluation).

About

image processing task I did using fine-tuning, DCNNs and common data augmentation techniques. dataset consisted of 1600 x-ray images of human stomach which included 800 each of pylori(helicobacter) positive and negative. augmented the dataset using common data augmentation techniques.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages