Tutorial
Let us start an interactive session (e.g. with python
or ipython
) and import Theano.
- >>> from theano import *
Several of the symbols you will need to use are in the tensor
subpackageof Theano. Let us import that subpackage under a handy name likeT
(the tutorials will frequently use this convention).
- >>> import theano.tensor as T
If that succeeded you are ready for the tutorial, otherwise check yourinstallation (see Installing Theano).
Throughout the tutorial, bear in mind that there is a Glossary as wellas index and modules links in the upper-right corner of each page to helpyou out.
Prerequisites
Basics
- Baby Steps - Algebra
- More Examples
- Derivatives in Theano
- Conditions
- Loop
- How Shape Information is Handled by Theano
Advanced
- Sparse
- Using the GPU
- Using multiple GPUs
Advanced configuration and debugging
- Configuration Settings and Compiling Modes
- Printing/Drawing Theano graphs
- Debugging Theano: FAQ and Troubleshooting
- Isolating the Problem/Testing Theano Compiler
- Interpreting Error Messages
- Using Test Values
- “How do I Print an Intermediate Value in a Function?”
- “How do I Print a Graph?” (before or after compilation)
- “The Function I Compiled is Too Slow, what’s up?”
- “Why does my GPU function seem to be slow?”
- “How do I Step through a Compiled Function?”
- How to Use pdb
- Dumping a Function to help debug
- Dealing with NaNs
- Profiling Theano function
Further readings
当前内容版权归 deeplearning 或其关联方所有,如需对内容或内容相关联开源项目进行关注与资助,请访问 deeplearning .