/ImageClassifier

Primary LanguagePython

ImageClassifier

  • original image size (1 x 10 x 10), it is symmetric, use only the right-top quarter
  • 0: success, 1: failure (based on the top 20 quantile value of bandgap)
  • imbalanced data (80/20)

Models:

  1. CNN with data augmentation (i.e., random flip and random rotation) and imbalanced data sampler(pytorch, TLClassifier.py)
  2. Bayes CNN: Bayes by Backprop, local reparameterization trick, variational dropout
  3. SVM, KNN, Random Forest, and MLP with hyperparameter tuning (sklearn, sklearnClassifier.py)
  4. CNN regressor: zero_padding enlarging mode in Resize(), target variable normalization techniques (sklearn)

CNN (Modified LeNet)

CNN loss

CNN precision-recall curve

CNN confusion matrix

Bayes CNN (LeNet)

BCNN loss BCNN pr BCNN cm

SVM

SVM precision-recall curve

CNN regressor

CNN regressor loss

CNN regressor r2