Code Monkey home page Code Monkey logo

vbd_cxr's Introduction

README

Final Report:

https://sheldonsebastian.github.io/vbd_cxr/

Directory Structure:

Path Description
0_preprocessor Code to convert DICOM to png and resize images.
1_eda Code to perform EDA
2_data_split Code to split the data into train-validation-holdout
3_trainer Code to train classification models and object detection models.
4_saved_models Saved models are stored here. Download trained models from here
5_inference_on_holdout_10_percent Code to make predictions using classification, object detection, and ensemble models.
6_inference_on_kaggle_test_files Utility files to make Kaggle submissions
7_deployment_files Code related to Flask App
common Utility files for making coding easier
archived Contains Proof of Concepts and miscellaneous files for experimentation purposes
docs files related to GitHub website
input_data folder in which input data will be placed

Steps to replicate project:

  1. Download processed data from here and download external data from here and place in root directory as "input_data" folder name.

  2. To create data train-holdout split for classification and object detection models, run all scripts in 2_data_split in the order they appear.

  3. Download trained models from here or run all the scripts in 3_trainer.

  4. To make inference on holdout dataset using:

    a. classification models run all scripts in 5_inference_on_holdout_10_percent/1_classification_models folder.

    b. object detection model run all scripts in 5_inference_on_holdout_10_percent/2_object_detection_models folder.

    c. ensemble model run all scripts in 5_inference_on_holdout_10_percent/3_ensemble folder.

  5. To make inference on kaggle test dataset run all scripts in 6_inference_on_kaggle_test_files folder.

Additional Packages required:

  1. albumentations
  2. pytorch
  3. detectron2
  4. ensemble-boxes
  5. Mean-Average-Precision-for-Boxes
  6. YOLOv5

vbd_cxr's People

Contributors

sheldonsebastian avatar guluna avatar

Watchers

 avatar

Forkers

guluna

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.