TensorFlow in Action

14 TensorBoard: Big brother of TensorFlow

This chapter covers

• Running and visualizing image data in TensorBoard
• Monitoring model performance and behaviors in real time
• Performance profiling models using TensorBoard
• Using tf.summary to log custom metrics during customized model training
• Visualizing and analyzing word vectors on TensorBoard

Thus far we have focused on various models. We have talked about fully connected models (e.g., autoencoders), convolutional neural networks, and recurrent neural networks (e.g., LSTMs, GRUs). In chapter 13, we talked about Transformers, a powerful family of deep learning models that have paved the way to a new state-of-the-art performance in language understanding. Furthermore, inspired by the achievements ...