This is more a conceptual question… Consider:
NoGradGuard guard;
b -= lr * b.grad();
I know that NoGradGuard
will disable action recording for the next gradient calculation.
But how does it really works?
This is more a conceptual question… Consider:
NoGradGuard guard;
b -= lr * b.grad();
I know that NoGradGuard
will disable action recording for the next gradient calculation.
But how does it really works?