ValueError: cannot convert float NaN to integer

tsinghua-rll / VoxelNet-tensorflow

A 3D object detection system for autonomous driving.

MIT License

453 stars 123 forks source link

ValueError: cannot convert float NaN to integer #13

Closed szm88 closed 6 years ago

szm88 commented 6 years ago

when I run test.py: FailedPreconditionError (see above for traceback): Attempting to use uninitialized value MiddleAndRPN_/conv7/kernel

jeasinema commented 6 years ago

Please provide more information about this error, like how to reproduce it.

xueyingliu commented 6 years ago

@szm88 I got similar problem when run test.py: the ret_box3d got a TypeError: 'NoneType' object is not iterable can you tell me how do you deal with your error? Thank you so much~