Zhiyong Wang

ME.cat() return SparseTensors must have the same coordinate_map_key

1

I have set input sparsetensor using same coordinate_manager ` sinput1 = ME.SparseTensor(features=input_dict['sinput_s_F'].to(self.device), coordinates=input_dict['sinput_s_C'].to(self.device), quantization_mode=ME.SparseTensorQuantizationMode.UNWEIGHTED_AVERAGE) sinput2 = ME.SparseTensor(features=input_dict['sinput_t_F'].to(self.device), coordinates=input_dict['sinput_t_C'].to(self.device), quantization_mode=ME.SparseTensorQuantizationMode.UNWEIGHTED_AVERAGE, coordinate_manager=sinput1.coordinate_manager)` after same network downsample, when i want to cat two...

Can't use SPARSE_NORMAL_CHOLESKY with Solver::Options::sparse_linear_algebra_library_type = SUITE_SPARSE, because support was not enabled when Ceres Solver was built.

1

I have build ceres with sparse and pass ./sparse_normal_cholesky_solver_test test. test output: `$ ./sparse_normal_cholesky_solver_test Running main() from gmock_main.cc [==========] Running 6 tests from 1 test suite. [----------] Global test environment...

how to use kinect_driver with cuda

1

i has alreday install cuda 8.0 。and souce the zshrc, after catkin_make and make libfreenect .when i launch kinect2_driver, it still use cpu, is something wrong about install cuda 8.0?