Search

We present a novel method for neural network quantization. Our method, named UNIQ, emulates a nonuniform k-quantile quantizer and adapts themodel to perform well with quantized weights by injecting noise to the weights at training time. As a by-product of injecting noise to weights, we find that activations can also be quantized to as low as 8-bit with only a minor accuracy degradation. Our non-uniform quantization approach provides a novel alternative to the existing uniform quantization techniques for neural networks. We further propose a novel complexity metric of number of bit operations performed (BOPs), and we show that this metric has a linear relation with logic utilization and power. We suggest evaluating the trade-off of accuracy vs. complexity (BOPs). The proposed method, when evaluated on ResNet18/34/50 and MobileNet on ImageNet, outperforms the prior state of the art both in the low-complexity regime and the high accuracy regime. We demonstrate the practical applicability of this approach, by implementing our non-uniformly quantized CNN on FPGA. [ABSTRACT FROM AUTHOR]

One major obstacle hindering the ubiquitous use of CNNs for inference is their relatively high memory bandwidth requirements, which can be the primary energy consumer and throughput bottleneck in hardware accelerators. Inspired by quantization-aware training approaches, we propose a compression-aware training (CAT) method that involves training the model to allow better compression of weights and feature maps during neural network deployment. Our method trains the model to achieve low-entropy feature maps, enabling efficient compression at inference time using classical transform coding methods. CAT significantly improves the state-of-the-art results reported for quantization evaluated on various vision and NLP tasks, such as image classification (ImageNet), image detection (Pascal VOC), sentiment analysis (CoLa), and textual entailment (MNLI). For example, on ResNet-18, we achieve near baseline ImageNet accuracy with an average representation of only 1.5 bits per value with 5-bit quantization. Moreover, we show that entropy reduction of weights and activations can be applied together, further improving bandwidth reduction. Reference implementation is available. [ABSTRACT FROM AUTHOR]