chapter seven

7 Teaching machines to see better: Improving CNNs and making them confess

 

This chapter covers

  • Reducing overfitting of image classifiers
  • Boosting model performance via better model architectures
  • Image classification using pretrained models and transfer learning
  • Modern ML explainability techniques to dissect image classifiers

7.1 Techniques for reducing overfitting

7.1.1 Image data augmentation with Keras

7.1.2 Dropout: Randomly switching off parts of your network to improve generalizability

7.1.3 Early stopping: Halting the training process if the network starts to underperform

7.2 Toward minimalism: Minception instead of Inception

7.2.1 Implementing the stem

7.2.2 Implementing Inception-ResNet type A block

7.2.3 Implementing the Inception-ResNet type B block

7.2.4 Implementing the reduction block

7.2.5 Putting everything together

7.2.6 Training Minception

7.3 If you can't beat them, join ‘em: Using pretrained networks for enhancing performance

7.3.1 Transfer learning: Reusing existing knowledge in deep neural networks

7.4 Grad-CAM: Making CNNs confess

Summary

Answers to exercises