Diabetic retinopathy is the leading cause of blindness in the working-age population of the developed world. It is estimated to affect over 93 million people.
I use Pytorch to handle this competition and get the accuracy of 85% in our test.
first, run pre_kaggle.py to pre-processing your image to get better accuracy and bold the feature which we need to clarify your images. For that, we use OpenCV that you have to install in your system. for train and test run main.py
- Python3
- Tensorboard
- Pytorch 0.3.0
- OpenCV
- Scikit-learn package
- Numpy
- OS
- python pre_kaggle.py
- python main.py