cipriancorneanu / dnn-topology

Computing topological cavities of deep neural networks
66 stars 12 forks source link

Question about build_graph_functional.py #2

Closed asier-gutierrez closed 4 years ago

asier-gutierrez commented 4 years ago

Dear Ciprian, your code looks amazing!

We are currently using it for some research but we found a line of code we can not understand. In this step of the code: https://github.com/cipriancorneanu/dnn-topology/blob/9c50a0883c6bfd92675a67828926196a6f95ffcc/build_graph_functional.py#L59

We do not get why you create two passers. We thought this could be related to reference passing and OOP stuff. We tried removing the "passer_test" variable and operating only with one passer and the results are the same. Is this an unintended code duplication or is it a bug?

Thank you for this interesting work!

asier-gutierrez commented 4 years ago

I found out that it is for convention in other similar scripts: https://github.com/cipriancorneanu/dnn-topology/blob/master/build_graph_functional_big_networks.py#L83

cipriancorneanu commented 4 years ago

Hi Asier, thanks for the interest. I am currently on vacation and I'll look into it as soon as I get back, probably next week.

Best,

On Tue, Aug 4, 2020, 17:01 Asier Gutiérrez notifications@github.com wrote:

Closed #2 https://github.com/cipriancorneanu/dnn-topology/issues/2.

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/cipriancorneanu/dnn-topology/issues/2#event-3620388696, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABWJIO2WZDQARVV7V4P4OBDR7AIFHANCNFSM4PUNMYXA .