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