search

NVIDIA / MinkowskiEngine

Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors
https://nvidia.github.io/MinkowskiEngine
Other
2.43k stars 360 forks source link

ME.cat() return SparseTensors must have the same coordinate_map_key #478

Open Yeah2333 opened 2 years ago

Yeah2333 commented 2 years ago

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 sparse tensor, it return AssertionError: SparseTensors must have the same coordinate_map_key.coordinate map key:[8, 8, 16] != coordinate map key:[8, 8, 16]:fa37J

zhuyinheng commented 2 years ago

save problem, even has the same hash code fa37j