View Code? Open in Web Editor
NEW
This project forked from sheldonsebastian/vbd_cxr
Detecting abnormalities in chest X-rays using object detection models. Secured rank 176 of 1277 participants (Top 14%)
Home Page: https://sheldonsebastian.github.io/vbd_cxr/
Python 0.52%
Jupyter Notebook 99.48%
vbd_cxr's Introduction
- Download processed data from .... and download external data from ... and place in root directory as "input_data" folder name.
- Run requirements.txt to install all required packages
- For training the models run ... or download trained models from ...
- For inference run the scripts ...
| Path |
Description |
| 0_preprocessor |
Code to convert DICOM to jpeg 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. Alternatively you can download them from ... |
| 5_inference |
Code to make predictions using classification, object detection, and ensemble models. |
| 6_kaggle_files |
Utility files to make Kaggle submissions |
| 7_deployment_files |
Code related to Flask App |
| common |
Utility files for coding |
vbd_cxr's People
Contributors
Watchers
React
Typescript
Django
Laravel
Facebook
Microsoft
Google
Alibaba
D3
Tencent