TensorBoard is a great interactive visualization tool that can be used to view the learning curves during training, compare learning curves across multiple runs, analyze training metrics and many more. This tool is installed automatically with TensorFlow. As stated earlier, there are no predefined rules on how many hidden layers or how many neurons are best suited for a problem space. We can use a RandomizedSearchCV or a GridSearchCV to hyper tune a few parameters.
Oct-11-2020, 09:56:52 GMT