A few questions about add_graphSee original GitHub issue
Hi @lanpa , thanks for this amazing tool. I’m trying to use
add_graph in my own project, where I met these questions:
- How to use
add_graphin the training iteration? Am I supposed to initialize the
SummaryWriteroutside the main training loop and call
w.add_graphinside the loop? If so how do I get the model output? Or this feature is only possible for dummy input and being called only once? Why it’s necessary to feed input to the model? It would be nice if you can provide an example with
add_graphused in a complete project(instead of
- Does it support custom CUDA layer? I tried with a custom correlation layer, and no matter what kind of data is fed into the model(random or image) the custom correlation failed for unknown reason.
Thanks for your time!
- Created 6 years ago
- Comments:8 (4 by maintainers)
Top GitHub Comments
@JiamingSuen There is a hacky solution. Since you only need to draw once, and result is don’t care. You can replace the GPU module with the following.
def forward(self, x):
# implement a fake correlation
#(as long as the output size is the same as real correlation)
I will give a shot on the real GPU code in the weekend.