Notes on instrumenting forward and backward prop

Some notes to myself on how to analyze different layers of a convolutional neural network.

In net.cpp, there are two functions

forwardDebugInfo(layerId) and backwardDebugInfo(layerId). They show you how to play with the blob data at the right place.

The two functions are called at the end of forwardFromTo and backwardFromTo in net.cpp.

To enable the debug functions, you can set a flag in your solver.protoxt

debug_info: true

This entry was posted in Convoluted Neural Nets. Bookmark the permalink.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s