Tensorflow 2.0: Solving Classification and Regression Problems

By the end of the 50th epoch, we have training accuracy of 100% while validation accuracy of 98.56%, which is impressive. Let's finally evaluate the performance of our classification model on the test set: Our model achieves an accuracy of 97.39% on the test set. Though it is slightly less than the training accuracy of 100%, it is still very good given the fact that we randomly chose the number of layers and the nodes. You can add more layers to the model with more nodes and see if you can get better results on the validation and test sets. In regression problem, the goal is to predict a continuous value. In this section, you will see how to solve a regression problem with TensorFlow 2.0 The dataset for this problem can be downloaded freely from this link.