Technical Deep Dive into a PyTorch Code Sample to Unpack Andrej Karpathy’s Six Most Common Neural Net Mistakes.

It takes years to build intuition and tricks of the trade. Alternatively, we can learn the basics from the greats and focus on greater challenges. With deep learning and computer vision, there are many pitfalls and hacks to work around and debug them. On June 30th, 2018, Andrej Karpathy, Director of AI at Tesla, tweeted a short list of first things to check when your neural network isn’t working.

Join me for this session where you will learn how to apply these lessons to our own neural networks. Using a computer vision dataset and a PyTorch code sample - we’ll walk through each of these pieces of advice, test it and explain it. Expect a technical deep dive and a review of best practices when debugging a PyTorch computer vision experiment.

Original tweet at: https://twitter.com/karpathy/status/1013244313327681536
188f95b26b1c
2997549-1546994927
Developer Relations at MissingLink
Data connoisseur and software engineer for 12 years in a variety of fields including a computer vision blood test for malaria, AAA games company and deep learning tools.
Share