Yuanpu Xie

@rarilurelo thanks for your reply. Can I simply set the state of pytorch optimizer to shared_memory() and add a lock to protect it. In this way, the copy of the...

add a function to component.cpp ``` void Component::set_timestep(int value) { _timestep = value; return ; } ``` add the function declaration in component.h then in pybrainbridge.py add the following :...

run the link command manually by removing ID=2, and you will be good

> --disable-model-loading-ram-optimization where should I put this line ?

Thanks for your reply. I am not sure what do you mean by slice the inputs. Is it about cropping the whole data (e.g. image) into many small squares? I...

@EderSantana

Sorry for the confusion！ taps can be found in the following code snept. In this case, the taps are defined before the loops start. But in 2D case, I might...

If the input is tensor, then it will call the torch.cumprod. But if the input is variable, it will call the custom cumprod which is written using autograd torch function....

For example, index_mapper is a leaf node, so it doesn't matter that it is constructed online from a numpy array during the process. For the gradient of cumprod, please take...

the custom `cumprod` should work well with autograd, cause it is implemented based on the autograd torch function.