TedNet: A Pytorch Toolkit for Tensor Decomposition Networks
This work provides a practical toolkit for researchers in machine learning to easily build and experiment with TDNs, which are incremental in offering pre-implemented methods rather than novel algorithmic advances.
The authors introduced TedNet, a PyTorch toolkit that implements five tensor decomposition methods (CP, BTT, Tucker-2, TT, TR) for convolutional and fully-connected layers to enable flexible construction of Tensor Decomposition Networks (TDNs), providing researchers with an accessible resource for exploiting compact neural architectures.
Tensor Decomposition Networks (TDNs) prevail for their inherent compact architectures. To give more researchers a flexible way to exploit TDNs, we present a Pytorch toolkit named TedNet. TedNet implements 5 kinds of tensor decomposition(i.e., CANDECOMP/PARAFAC (CP), Block-Term Tucker (BTT), Tucker-2, Tensor Train (TT) and Tensor Ring (TR) on traditional deep neural layers, the convolutional layer and the fully-connected layer. By utilizing the basic layers, it is simple to construct a variety of TDNs. TedNet is available at https://github.com/tnbar/tednet.