The key idea of deep learning lies in the construction of deep neural networks. If you start to build a deep neural network by yourself from the very beginning, the whole process will be complicated. Therefore, in order to implement models of deep learning more easily, we need to grasp how to use some common deep learning frameworks. By now, in the deep learning community, the most popular frameworks are TensorFlow and PyTorch, and they have their own unique characteristics. Because TensorFlow is supported by a giant named Google along with the huge community composed of developers with its fast update and release cycles, understanding and mastering the use of TensorFlow will help you more when building deep learning models.