Add New Metrics¶
Develop with the source code of MMSegmentation¶
Here we show how to develop a new metric with an example of
CustomMetric as the following.
Create a new file
from typing import List, Sequence from mmengine.evaluator import BaseMetric from mmseg.registry import METRICS @METRICS.register_module() class CustomMetric(BaseMetric): def __init__(self, arg1, arg2): """ The metric first processes each batch of data_samples and predictions, and appends the processed results to the results list. Then it collects all results together from all ranks if distributed training is used. Finally, it computes the metrics of the entire dataset. """ def process(self, data_batch: dict, data_samples: Sequence[dict]) -> None: pass def compute_metrics(self, results: list) -> dict: pass def evaluate(self, size: int) -> dict: pass
In the above example,
CustomMetricis a subclass of
BaseMetric. It has three methods:
process()process one batch of data samples and predictions. The processed results are stored in
self.resultswhich will be used to compute the metrics after all the data samples are processed. Please refer to MMEngine documentation for more details.
compute_metrics()is used to compute the metrics from the processed results.
evaluate()is an interface to compute the metrics and return the results. It will be called by
Runner. In most cases, you don’t need to override this method, but you can override it if you want to do some extra work.
Note: You might find the details of calling
evaluate()method in the
Runneris the executor of the training and testing process, you can find more details about it at the engine document.
Import the new metric in
from .custom_metric import CustomMetric __all__ = ['CustomMetric', ...]
Add the new metric to the config file.
val_evaluator = dict(type='CustomMetric', arg1=xxx, arg2=xxx) test_evaluator = dict(type='CustomMetric', arg1=xxx, arg2=xxx)
Develop with the released version of MMSegmentation¶
The above example shows how to develop a new metric with the source code of MMSegmentation. If you want to develop a new metric with the released version of MMSegmentation, you can follow the following steps.
Create a new file
/Path/to/metrics/custom_metric.py, implement the
evaluatemethod is optional.
Import the new metric in your code or config file.
from path.to.metrics import CustomMetric
custom_imports = dict(imports=['/Path/to/metrics'], allow_failed_imports=False) val_evaluator = dict(type='CustomMetric', arg1=xxx, arg2=xxx) test_evaluator = dict(type='CustomMetric', arg1=xxx, arg2=xxx)