Non Pneumonia
A Deep Learning based model used for the prediction whether a person is suffering from pneumonia or not. The project is absed upon the Standard Convolutional Based Neural Network Architectural Implementation. It incorporates the use of CNN layers with Hyper-parameters tuning. The motivation behind the project is to effectively classify the reports of chest xrays to classify into pneumonia or non-pneumonia cases.
The model has been trained for 12 epoch. The model gave an accuracy of 98.51 on validation sets.
Case of Pneumonia
The dataset used can be downloaded here - Click to Download
This dataset consists of images belonging to 2 classes:
Our model is capable of predicting Pneumonia from chest x-ray images with high efficiency. These predicted images are converted to grayscale version for predictions.
The model is efficient, since we used a compact CNN-based architecture, it’s also computationally efficient and thus making it easier to deploy the model to servers.
All the dependencies and required libraries are included in the file requirements.txt See here
-
Start and fork the repository.
-
Clone the repo
$ git clone https://github.com/beingaryan/Chest-Xray-Pneumonia-Prediction.git
- Change your directory to the cloned repo and create a Python virtual environment named 'test'
$ mkvirtualenv test
- Now, run the following command in your Terminal/Command Prompt to install the libraries required
$ pip3 install -r requirements.txt
- Open terminal. Go into the cloned project directory and type the following command:
$ python3 jupyter
- To train the model, open the Pneumonia_Prediction file in jupyter notebook and run all the cells
* The model has been trained on a python based environment on Jupyter platform. * The model is iterated for a total epoch of 12. * The model has attained an accuracy of __98.51 %__ accuracy on the Validation set.
Feel free to mail me for any doubts/query :email: aryan.gupta18@vit.edu
Feel free to file a new issue with a respective title and description on the the Pneumonia_Detection repository. If you already found a solution to your problem, I would love to review your pull request!
Made with ❤️ by Aryan Gupta
You can find our Code of Conduct here.
MIT © Aryan Gupta