which open3d version to use?

[jerinka]

python mainTSDF_Integrate__color_depth.py Traceback (most recent call last): File "mainTSDF_Integratecolor_depth.py", line 156, in result_ransac = execute_global_registration(source_down, target_down, File "mainTSDF_Integrate__color_depth.py", line 67, in execute_global_registration result = o3d.pipelines.registration.registration_ransac_based_on_feature_matching( TypeError: registration_ransac_based_on_feature_matching(): incompatible function arguments. The following argument types are supported:

1. (source: open3d.cuda.pybind.geometry.PointCloud, target: open3d.cuda.pybind.geometry.PointCloud, source_feature: open3d::pipelines::registration::Feature, target_feature: open3d::pipelines::registration::Feature, mutual_filter: bool, max_correspondence_distance: float, estimation_method: open3d.cuda.pybind.pipelines.registration.TransformationEstimation = TransformationEstimationPointToPoint without scaling., ransac_n: int = 3, checkers: List[open3d.cuda.pybind.pipelines.registration.CorrespondenceChecker] = [], criteria: open3d.cuda.pybind.pipelines.registration.RANSACConvergenceCriteria = RANSACConvergenceCriteria class with max_iteration=100000, and confidence=9.990000e-01) -> open3d.cuda.pybind.pipelines.registration.RegistrationResult

Invoked with: PointCloud with 2923 points., PointCloud with 2580 points., Feature class with dimension = 33 and num = 2923 Access its data via data member., Feature class with dimension = 33 and num = 2580 Access its data via data member., 0.015, TransformationEstimationPointToPoint without scaling., 4, [CorrespondenceCheckerBasedOnEdgeLength with similarity_threshold=0.900000, CorrespondenceCheckerBasedOnDistance with distance_threshold=0.015000], RANSACConvergenceCriteria class with max_iteration=4000000, and confidence=1.000000e+00

[jerinka]

sorry its mentioned in readme, I didnt notice, open3d==0.9.0.0