search

infocusp / tf_cnnvis

CNN visualization tool in TensorFlow
MIT License
781 stars 209 forks source link

Questions on Example 3, sessions and graphs #31

Closed csggnn closed 6 years ago

csggnn commented 6 years ago

I the 3 examples, the activation functions are taking graphs as input and producing visualizations as output. As a graph only stores the structure of the network and not the actual weight values, how can the visualization functions have access to these values? To my understanding in example 1 the the default values for the graph nodes are visualized, in example 2 there seems to be a solvable problem, but how about Example 3? I see a tmp_model folder which could hold the data needed to restore the variable values, but where is this data in tmp_model generated? Thank you for your help and patience

csggnn commented 6 years ago

Closing this issue. For futre reference, graph in example 3 was frozen, its variables converted to constants, this is how their value could be retained by the graph.