We can also represent these data as sparse tensors, and these sparse tensors are commonplace in high-dimensional problems such as 3D perception, registration, and statistical data. However, in this work, we focus on spatially sparse data, in particular, spatially sparse high-dimensional inputs and 3D data and convolution on the surface of 3D objects, first proposed in Siggraph’17. Such parameter-space sparsity used for model compression compresses networks that operate on dense tensors and all intermediate activations of these networks are also dense tensors. One of the popular techniques for model compression is pruning the weights in convnets, is also known as sparse convolutional networks. Sparse Tensor Networks: Neural Networks for Spatially Sparse Tensors ¶Ĭompressing a neural network to speedup inference and minimize memory footprint has been studied widely.

Forward and backward using the custom network.CPU only build and BLAS configuration (MKL).