Help Needed ---- Getting Gradients in Multiprocessing


I am currently using examples/ at master · pytorch/examples ( for multiprocessing startup for my code. I used the below line to print my gradients but all them are NONE. So is there anyway to get these gradients.

I need the gradients somehow any help would be greatly appreciated.

for name, param in model.named_parameters():

I even used the args.num_process=1 but the output is still the same

conv1.weight None
conv1.bias None
conv2.weight None
conv2.bias None
fc1.weight None
fc1.bias None
fc2.weight None
fc2.bias None

I even tried to use multiprocessing queue to return the gradients but the problem is that queue is not able to return that big size of the gradients.