zleyk22 opened a new issue #17864: An incorrect result generated by exec.backward URL: https://github.com/apache/incubator-mxnet/issues/17864 ## Description I run the python program below and I get a wrong result (`nan`) ## To Reproduce This is a python program I run: ``` import mxnet as mx sym = mx.symbol.prod(data=mx.symbol.Variable("in"), axis=(1)) exec = sym.bind(mx.cpu(0), {"in":mx.nd.array([[4, 0]])}, {"in":mx.nd.array([[9, 9]])}) out = exec.forward()[0] print('-- Output:') print(exec.outputs) exec.backward(mx.nd.ones(out.shape)) print('-- Gradient:') print(exec.grad_dict['in']) ``` I get this output: ``` -- Output: [ [0.] <NDArray 1 @cpu(0)>] -- Gradient: [[ 0. nan]] <NDArray 1x2 @cpu(0)> ``` But I expected to get this result instead of `[[0. nan]]`: ``` [[0. 4.]] ``` I cannot explain why I get `nan`. It would be helpful if somebody can help me with this. ## Environment I use MXNet 1.6.0 and run python 3.7.7 (with ipython 7.13.0)
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
