A supervised classification model, which predicts the labels of a Modified MNIST dataset. 1st place in Kaggle competition (https://www.kaggle.com/c/modified-mnist/overview)
0
stars
0
forks
source link
Create a script to process the regular MNIST database to go through the same preprocessing pipeline #5
If we pass the MNIST dataset through the same preporcessing pipeline as our data, the orientations of the numbers as well as the brightness of each pixels is more likely to match and increase the prediction accuracy.
We need a script that can create a custom MNIST dataset that went through our proprocessing pipeline
If we pass the MNIST dataset through the same preporcessing pipeline as our data, the orientations of the numbers as well as the brightness of each pixels is more likely to match and increase the prediction accuracy.
We need a script that can create a custom MNIST dataset that went through our proprocessing pipeline