I try to print loss.backward() then I got none,but the network training is still running.
Why ?
1 Like
tensor.backward()
won’t return anything. Instead the .grad
attributes of all parameters used to compute the loss will be populated and accumulated.
1 Like
so should i print param_name.grad?
1 Like
it will compute backpropogation. if you want to compute manually use torch.no_grad()
Yes, if you want to print out all gradients, you could use:
print(model.layer.param.grad)
# or to print all gradients
for name, param in model.named_parameters():
print(name, param.grad)
1 Like
Thank you very much.