🩺 X-Ray-Image-Classification

Comparative Analysis of Convolutional Neural Networks for X Ray 🩺 Image Analysis. Check out the Deepnote Kernel used for modeling and experimentation.

A Complete End to End Deep Learning Project, going over Modelling, Ablation Studies, Post-Training Quantization and Deployment using Streamlit and Tensorflow Serving.

Model Type	Total Parameters	Trainable Parameters	Non-Trainable Parameters
EfficientNetB0 + Classification Head	4,059,828	10,257	4,049,571

The Data used in this project is available at the Activeloop platform in 3 sub-splits. Each subset can be found at:

• Training Subset
• Validation Subset
• Test Subset

Developer Toolkit

Metrics

Weights and Biases client was used for model monitoring, for more details please visit the project page.

Exploratory Data Analysis

Label Distribution

Ben Graham's Method

Background Subtraction

Fourier Method for Pixel Distribution

Canny Edge Detection

GradCAM

The Colab Notebook used for obtaining this image can be found in the notebooks/ folder.

Docker Instructions

docker pull docker.pkg.github.com/sauravmaheshkar/x-ray-image-classification/xray-streamlit:v0.0.1
docker run -p 8501:8501 xray-streamlit:latest

Contribute

If you want to contribute to the project kindly mail me at [email protected].

Step 1

• Option 1 🍴 Fork it!
• Option 2 👯‍♂️ Clone this repo to your local machine using https://github.com/SauravMaheshkar/X-Ray-Image-Classification.git

Step 2

• HACK AWAY! 🔨🔨🔨

Step 3

• 🔃 Create a new pull request using https://github.com/SauravMaheshkar/X-Ray-Image-Classification/compare/

License

The data for this project was taken from kaggle datasets. You can find the Chest X-Ray Images (Pneumonia) Dataset here.

• Copyright 2020 @Saurav Maheshkar
• MIT License

Credits

The inspiration for this readme file came from

• fvcproductions
• Navendu Pottekkat