Questions

1. What are VGG and ResNet pre-trained architectures trained on?
2. Why does VGG11 have an inferior accuracy to VGG16?
3. What does the number 11 in VGG11 represent?
4. What does the term residual mean in “residual network” refer to?
5. What is the advantage of a residual network?
6. What are the various popular pretrained models discussed in the book and what is the speciality of each network?
7. During transfer learning, why should images be normalized with the same mean and standard deviation as those that were used during the training of the pre-trained model?
8. When and why do we freeze certain parameters in a model?
9. How do we know the various modules that are present in a pre-trained model?
10. How do we train a model that predicts categorical and numerical values together?
11. Why might age and gender prediction code not always work for an image of your own if we were to execute the same code as that which we wrote...