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 validation pipeline for the MaxMNIST model #7
We need a validation pipeline that will evaluate our model, get the accuracy score, and produce a confusion matrix of our prediction as well as calculate where the proportion of our predictions are.
Since the dataset is unbalanced, and there are only about 0.8% of samples that have the label 0, we have a problem is we are predicting 0, 10% of the time
vaquierm
commented
5 years ago
We need a validation pipeline that will evaluate our model, get the accuracy score, and produce a confusion matrix of our prediction as well as calculate where the proportion of our predictions are.
Since the dataset is unbalanced, and there are only about 0.8% of samples that have the label 0, we have a problem is we are predicting 0, 10% of the time