Forward and Backward Propagation

[ksarker1205]

I am interested to see where forward and backward propagation is happening in the code. Can you point me to that specific portion of the code ?

[hma02]

Hi @ksarker1205 , when the computing graph is compiled into a theano function, the forward and backward propagation happens each time the function is called at this line:
https://github.com/uoguelph-mlrg/theano_alexnet/blob/master/train_funcs.py#L165

The function is responsible for taking the input and forward propagating through the graph, and the update argument of the function specifies how the gradient is used in backward propagation.

See how the theano function is constructed here:
https://github.com/uoguelph-mlrg/theano_alexnet/blob/master/alex_net.py#L216