Metric: r2

[rijobro]

Description

Implements r2 metric to compare similarities between two tensors. This is a useful metric as it can be expressed as a percentage, as opposed to MSE for example which is arbitrary.

Useful in image regression.

Status

Ready

Types of changes

• [x] Non-breaking change (fix or new feature that would not break existing functionality).
• [x] New tests added to cover the changes.
• [x] Integration tests passed locally by running ./runtests.sh -f -u --net --coverage.
• [x] Quick tests passed locally by running ./runtests.sh --quick --unittests --disttests.
• [x] In-line docstrings updated.
• [x] Documentation updated, tested make html command in the docs/ folder.

[wyli]

/build

[KumoLiu]

Hi @rijobro, I wonder why assign y.sum(1) to two different variables (n and sum_y). And I didn't find the definition of the mean of the observed data which needed by R2 metric definition. I'm not sure whether it is a variation of the original formula or maybe just I misunderstood. Thanks.