the error of backpropagation #2906
xuhongxin
started this conversation in
Deep Learning
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
i was study the Section 2.5(Automatic Differentiation), but when i run the follow demo code , it report the error;what is the reason of the error?
the demo code
try (GradientCollector gc = Engine.getInstance().newGradientCollector()) { NDArray y = x.sum(); gc.backward(y); } x.getGradient() // Overwritten by the newly calculated gradient
the error
`
ai.djl.engine.EngineException: MXNet engine call failed: MXNetError: Check failed: !AGInfo: :IsNone(*i): Cannot differentiate node because it is not in a computational graph. You need to set is_recording to true or use autograd.record() to save computational graphs for backward. If you want to differentiate the same graph twice, you need to pass retain_graph=True to backward.
Stack trace:
File "/Users/runner/work/djl/djl/src/imperative/imperative.cc", line 295
`
Beta Was this translation helpful? Give feedback.
All reactions