Quantaized Winograd/Toom-Cook Convolution for DNNs: Beyond Canonical Polynomials Base

Abstract: The problem how to speed up the convolution computations in Deep Neural Networks is widely investigated in recent years. The Winograd convolution algorithm is a common used method that significantly reduces time consumption. However, it suffers from a problem with numerical accuracy particularly for lower precisions. In this paper we present the application of base change technique for quantized Winograd-aware training model. We show that we can train the $8$ bit quantized network to nearly the same accuracy (up to 0.5% loss) for tested network (Resnet18) and dataset (CIFAR10) as for quantized direct convolution with few additional operations in pre/post transformations. Keeping Hadamard product on $9$ bits allow us to obtain the same accuracy as for direct convolution.