This repository has been archived by the owner on Nov 17, 2023. It is now read-only.
Confusing behavior of some evaluation metrics #9865
Comments
Thanks for reporting this, we will improve our documentation and support NDArray as the input. |
I find this is actually a bug. The |
7 tasks
szha
pushed a commit
that referenced
this issue
Mar 13, 2018
* fix #9865 * add unittest * fix format * fix format * fix superfluous loop in metric * fix lint
jinhuang415
pushed a commit
to jinhuang415/incubator-mxnet
that referenced
this issue
Mar 30, 2018
* fix apache#9865 * add unittest * fix format * fix format * fix superfluous loop in metric * fix lint
szha
pushed a commit
that referenced
this issue
May 1, 2018
* fix #9865 * add unittest * fix format * fix format * fix superfluous loop in metric * fix lint * update resnet18/34 in the gluon model zoo * correct values
anirudh2290
pushed a commit
to anirudh2290/mxnet
that referenced
this issue
May 7, 2018
* fix apache#9865 * add unittest * fix format * fix format * fix superfluous loop in metric * fix lint * update resnet18/34 in the gluon model zoo * correct values
rahul003
pushed a commit
to rahul003/mxnet
that referenced
this issue
Jun 4, 2018
* fix apache#9865 * add unittest * fix format * fix format * fix superfluous loop in metric * fix lint
rahul003
pushed a commit
to rahul003/mxnet
that referenced
this issue
Jun 4, 2018
* fix apache#9865 * add unittest * fix format * fix format * fix superfluous loop in metric * fix lint * update resnet18/34 in the gluon model zoo * correct values
zheng-da
pushed a commit
to zheng-da/incubator-mxnet
that referenced
this issue
Jun 28, 2018
* fix apache#9865 * add unittest * fix format * fix format * fix superfluous loop in metric * fix lint
zheng-da
pushed a commit
to zheng-da/incubator-mxnet
that referenced
this issue
Jun 28, 2018
* fix apache#9865 * add unittest * fix format * fix format * fix superfluous loop in metric * fix lint * update resnet18/34 in the gluon model zoo * correct values
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
According to the API document, the
update
method of evaluation metrics takes lists of NDArrays. So the first example uses the API not correctly, but there is no errors or warnings. Many functions of mxnet allow "an NDArray or a list of NDArrays" as an argument and an NDArray is equivalent to a list with a single element. So this behavior of the MSE metric is confusing and errorprone. Please raise an error or fix the implementation for NDArray arguments.When I give NDArrays as arguments instead of lists to call
Accuracy.update
, a segfault occurs with the following error and stacktrace.This is much more acceptable than meaningless results without any error but not graceful.
The result of this example is not understandable. I believe the result should be 0.01 in this case also. Or, if 1D array is not acceptable, it must raise an error.
MAE, RMSE and PearsonCorrelation also show similar behavior.
The text was updated successfully, but these errors were encountered: