Is it possible to show which layer is the current layer connected to?

[keykeykeykeyk]

The current version of model summary works perfectly on sequential model. However, sometimes the architecture could be complex. In keras, when summarize the the model created by the callable layer instance, there is an additional column that shows where the layer is conntected to. Could pytorch_model_summary also support this?

An example of summary() in keras:

[amarczew]

@keykeykeykeyk I planned to have this, but when I created the first version I didn't find an easy way to do this. Unfortunately I haven't worked with pytorch for the last months and I didn't have time later to implement this. I also created this issue #1 to remember to add this later.

I really liked that information in keras and I would like to add this in this library as well. If you have any idea or implementation doing this, feel free to send a PR.

thanks for the feedback :D