Open wangx1996 opened 5 years ago
These warnings don't seem to have any impact and the network can be trained and tested properly. If you're in trouble, you can block these warnings.
These warnings don't seem to have any impact and the network can be trained and tested properly. If you're in trouble, you can block these warnings.
Yes,you r right. These warnings don't impact the training. Thank you.
numba 0.44 started showing some deprecation warnings that mostly help users identify more rooms for optimization, see here for more details.
You can use numba 0.43.1 if you don't want to see these warnings.
Compilation is falling back to object mode WITH looplifting enabled because Function "points_in_convex_polygon_jit" failed type inference due to: Invalid use of Function() with argument(s) of type(s): (array(float32, 3d, C), (slice, list(int64), slice))
File "../../second.pytorch-master/second/core/geometry.py", line 153: def points_in_convex_polygon_jit(points, polygon, clockwise=True):