Modular metrics #71
Modular metrics #71
Conversation
Signed-off-by: neuronflow <[email protected]>
…s matching metric and threshold to make evaluator give a better overview
Signed-off-by: neuronflow <[email protected]>
Signed-off-by: neuronflow <[email protected]>
|
Probably we should close the pr until it is ready to merge? |
|
ouch we now have conflicts with main here 🙈 |
…ed string and dict representation
|
🤖 Code Formatting Reminder Hello there! 👋 It looks like the code in this pull request might benefit from some formatting improvements. |
|
/format |
|
🤖 I will now format your code with black. Check the status here. |
examples/example_cfos_3d.py
Outdated
| @@ -21,7 +21,7 @@ | |||
| expected_input=SemanticPair, | |||
| instance_approximator=ConnectedComponentsInstanceApproximator(), | |||
| instance_matcher=NaiveThresholdMatching(), | |||
| iou_threshold=0.5, | |||
| match_threshold=0.5, | |||
There was a problem hiding this comment.
should it be called match or matching threshold?
benchmark/modules_speedtest.py
Outdated
| @@ -89,7 +89,7 @@ def test_input(processing_pair: SemanticPair): | |||
| # | |||
| start3 = perf_counter() | |||
| processing_pair = evaluate_matched_instance( | |||
| processing_pair, iou_threshold=iou_threshold | |||
| processing_pair, matching_threshold=iou_threshold | |||
|
🤖 Code Formatting Reminder Hello there! 👋 It looks like the code in this pull request might benefit from some formatting improvements. |
|
/format |
|
🤖 I will now format your code with black. Check the status here. |
No description provided.