Introduction to TensorFlow
TensorFlow is written in C++ and comprises two languages in the frontend. They are C++ and Python. Since most developers code in Python, the Python frontend is more developed than the C++ one. However, the C++ frontend's low-level API is good for running embedded systems.
TensorFlow was designed for probabilistic systems and gives flexibility to users to run models with ease, and across a variety of platforms. With TensorFlow, it is extremely easy to optimize various machine learning algorithms without having to set gradients at the beginning of the code, which is quite difficult. TensorFlow comes packed with TensorBoard, which helps visualize the flow with graphs and loss functions. The following screenshot shows ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access