MCPcopy Create free account
hub / github.com/NVIDIA/MinkowskiEngine / generate_input_sparse_tensor

Function generate_input_sparse_tensor

tests/python/strided_conv.py:74–81  ·  view source on GitHub ↗
(file_name, voxel_size=0.05, batch_size=1)

Source from the content-addressed store, hash-verified

72
73
74def generate_input_sparse_tensor(file_name, voxel_size=0.05, batch_size=1):
75 # Create a batch, this process is done in a data loader during training in parallel.
76 batch = [load_file(file_name, voxel_size),] * batch_size
77 coordinates_, featrues_, pcds = list(zip(*batch))
78 coordinates, features = ME.utils.sparse_collate(coordinates_, featrues_)
79
80 # Normalize features and create a sparse tensor
81 return features, coordinates
82
83
84if __name__ == "__main__":

Callers 1

strided_conv.pyFile · 0.70

Calls 1

load_fileFunction · 0.70

Tested by

no test coverage detected