Overview
Why is deep learning troubleshooting hard?
Overview - Troubleshooting
- A common sentiment among practitioners is that they spend 80–90% of time debugging and tuning the models, and only 10–20% of time deriving math equations and implementing things.
- Reproducing the results in deep learning can be challenging due to various factors including implementation bugs, choices of model hyper-parameters, data/model fit, and the construction of data.
Last modified 2yr ago