-
-
Notifications
You must be signed in to change notification settings - Fork 617
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Mean Absolute Percentage Error (MAPE) #3198
Comments
@aalbayrak394 thanks for asking, EDIT: sorry, misread mean vs median.
OK, MAPE is also MARE: https://pytorch.org/ignite/v0.4.13/generated/ignite.contrib.metrics.regression.MeanAbsoluteRelativeError.html#ignite.contrib.metrics.regression.MeanAbsoluteRelativeError Let's make a shortcut and improve docs for better discovery. |
Sure, that would make more sense. Maybe adding ", also known as Mean Absolute Percentage Error" to the first line of the doc would do it? |
Yeah, and also add "(MAPE)" and "(MARE)" like that:
|
I created a PR #3199 |
@vfdev-5 How comes that some CI tests are failing when I only changed a line in the docstring? |
@aalbayrak394 some CI tests are flaky and some of them are broken right now. For example, https://github.com/pytorch/ignite/actions/workflows/triage.yml, where I upgraded |
🚀 Feature
I'd like to implement the mean absolute percentage error (MAPE) in
ignite/metrics
.It is a commonly used metric for regression problems and it would be really convenient to be able to use it directly with ignite evaluators.
For that, I would write a custom Metric class in a new file
mean_absolute_percentage_error.py
inheriting from the baseMetric
class inignite/metrics/metric.py
.The text was updated successfully, but these errors were encountered: