Log In Sign Up

FINN: A Framework for Fast, Scalable Binarized Neural Network Inference

by   Yaman Umuroglu, et al.

Research has shown that convolutional neural networks contain significant redundancy, and high classification accuracy can be obtained even when weights and activations are reduced from floating point to binary values. In this paper, we present FINN, a framework for building fast and flexible FPGA accelerators using a flexible heterogeneous streaming architecture. By utilizing a novel set of optimizations that enable efficient mapping of binarized neural networks to hardware, we implement fully connected, convolutional and pooling layers, with per-layer compute resources being tailored to user-provided throughput requirements. On a ZC706 embedded FPGA platform drawing less than 25 W total system power, we demonstrate up to 12.3 million image classifications per second with 0.31 μs latency on the MNIST dataset with 95.8 283 μs latency on the CIFAR-10 and SVHN datasets with respectively 80.1 and 94.9 classification rates reported to date on these benchmarks.


page 1

page 2

page 3

page 4


Scaling Binarized Neural Networks on Reconfigurable Logic

Binarized neural networks (BNNs) are gaining interest in the deep learni...

LUTNet: Learning FPGA Configurations for Highly Efficient Neural Network Inference

Research has shown that deep neural networks contain significant redunda...

TinBiNN: Tiny Binarized Neural Network Overlay in about 5,000 4-LUTs and 5mW

Reduced-precision arithmetic improves the size, cost, power and performa...

LUTNet: Rethinking Inference in FPGA Soft Logic

Research has shown that deep neural networks contain significant redunda...

Unrolling Ternary Neural Networks

The computational complexity of neural networks for large scale or real-...

CodeX: Bit-Flexible Encoding for Streaming-based FPGA Acceleration of DNNs

This paper proposes CodeX, an end-to-end framework that facilitates enco...

fpgaConvNet: A Toolflow for Mapping Diverse Convolutional Neural Networks on Embedded FPGAs

In recent years, Convolutional Neural Networks (ConvNets) have become an...