A place for tuning related questions. Tuning questions are those like “what settings should I use for my net?” or “why am I getting poor performance from my network?”.
Providing help for tuning neural networks can be quite time consuming for the development team, and takes away from other efforts (such as adding features, improving performance, improving documentation or fixing bugs). In order to keep the support load under control, please be aware of the following policy:
- Before posting a question, please first read both Troubleshooting Neural Net Training and Visualize, Monitor And Debug Neural Network Learning. You may also find an answer to your question on one of the other pages: https://deeplearning4j.org/docs/latest/
- We generally won’t answer questions that can be easily answered by searching Google or reading something like Andrej Karpathy’s Stanford course on convolutional networks http://cs231n.github.io/ or Ian Goodfellow and Yoshua Bengio’s deep learning book http://www.deeplearningbook.org/
- For some questions/issues, it may not be possible to provide a short/simple answer to your question. In these cases, we might decide to answer your question by improving our documentation, instead of answering your question directly. Please understand that improving our documentation helps everyone and is a better use of the team’s time than answering one-off questions.
- You should generally feel free to open issues (https://github.com/eclipse/deeplearning4j/issues) if you feel our documentation (troubleshooting/tuning) is lacking or doesn’t answer common questions.
5 When starting a topic please tell us more than just “it doesn’t work”. Information-rich questions and comments are appreciated. Please keep the content relevant.