Questions

1. For classification of the mnist dataset using an FC layer with Keras, write a Python code fragment to visualize the output layer (what the neural network sees).
2. For classification of the mnist dataset using the neural network with FC layers only and with the CNN with Keras, we have directly used the test dataset for evaluating the model while training it. Set aside a few thousand images from training images and create a validation dataset and train the model on the remaining images. Use the validation dataset to evaluate the model while training. At the end of training, use the model learned to predict the labels of the test dataset and evaluate the accuracy of the model. Does it increase?

3. Use VGG-16/19, Resnet-50, and Inception V3 models (from Keras) to train (from scratch) on the mnist training images. What is the maximum accuracy you get on the test images?