Closed adrelino closed 3 years ago
Good spotting. This looks like some kind of matplotlib pixel rounding error.
Here are the numbers representing the total count of each FeatureOperation
in the dataset:
'NewBodyFeatureOperation': 10304
'JoinFeatureOperation': 4711
'CutFeatureOperation': 4299
'IntersectFeatureOperation': 19
As you can see the numbers of IntersectFeatureOperation
are very low, so it does not appear to be commonly used by designers/engineers using Fusion 360. My guess is that the other operations tend to be more intuitive to work with in most scenarios.
Oddly the low-res inline plot from a Jupyter Notebook seems to show a small blip for IntersectFeatureOperation
.
@adrelino I'm going to close this for now. Feel free to reopen if you have other questions.
Is there really no extrude
IntersectFeatureOperation
in the whole dataset according to the very bottom of the stats page (https://github.com/AutodeskAILab/Fusion360GalleryDataset/blob/master/docs/reconstruction_stats.md)?If so, what might be the reasons for that? Do users rarely extrude 2 shapes to later intersect them to get a smaller shape?
Isn't that a problem for an agent solving the gym environment, bootstrapped with imitiation learning from the reconstruction dataset, since the
IntersectFeatureOperation
action will get initialized with 0 probability and never be explored?