[Tensorflow vs. Pytorch] Become proficient in deep learning frameworks

Source: Deep Learning on Medium

[Tensorflow vs. Pytorch] Become proficient in deep learning frameworks

Today, deep learning is gaining strength due to rapid improvements in computing performance and the amount of data that is accumulated. Accordingly, IT Giants develop their deep learning framework to provide developers with a development environment, including Google’s Tensorflow and Facebook’s PyTorch.

Figure 1. Deep learning frameworks

Each framework has its characteristics and is properly used in the appropriate areas. For engineers with research purposes, it is necessary to note Figure 2. The recent trend in the papers uploaded on arXiv.org shows that TensorFlow and PyTorch are mainly used in research purposes.

Figure 2. The number of papers posted on arXiv.org that mention each framework. Source: Data from RISELab and graphic by Ben Lorica.

In the future, I will select various topics and upload a series of tutorials, and code will also be uploaded in two versions, Tensorflow and PyTorch. First of all, I will upload basic topics, such as the MNIST tutorial. After that, I will discuss energy-related time series data and reinforcement learning, which are my research interests. I hope this will help engineers who are new to using deep learning frameworks or would like to be more adept at dealing with them.