卷积神经网络混合截断量化

量化是压缩卷积神经网络、加速卷积神经网络推理的主要方法.现有的量化方法大多将所有层量化至相同的位宽,混合精度量化则可以在相同的压缩比下获得更高的准确率,但寻找混合精度量化策略是很困难的.为解决这种问题,提出了一种基于强化学习的卷积神经网络混合截断量化方法,使用强化学习的方法搜索混合精度量化策略,并根据搜索得到的量化策略混合截断权重数据后再进行量化,进一步提高了量化后网络的准确率.在ImageNet数据集上测试了ResNet18/50以及MobileNet-V2使用此方法量化前后的Top-1准确率,在COCO数据集上测试了YOLOV3网络量化前后的mAP.与HAQ, ZeroQ相比, MobileNet-V2网络量化至4位的Top-1准确率分别提高了2.7%和0.3%;与分层量化相比, YOLOV3网络量化至6位的mAP提高了2.6%.

Mixed-Clipping Quantization for Convolutional Neural Networks

Quantization is the main method to compress convolutional neural networks and accelerate convolutional neural network inference.Most existing quantization methods quantize all layers to the same bit width.Mixed-precision quantization can obtain higher precision under the same compression ratio,but it is difficult to find a mixed-precision quantization strategy.To solve this problem,a mixed-clipping quantization method based on reinforcement learning is proposed.It uses reinforcement learning to search for a mixed-precision quantization strategy,and uses a mixed-clipping method to clip weight data according to the searched quantization strategy before quantization.This method further improves the accuracy of the quantized network.We extensively test this method on a diverse set of models,including ResNet18/50,Mobile-Net-V2 on ImageNet,as well as YOLOV3 on the Microsoft COCO dataset.The experimental results show that our method can achieve 2.7%and 0.3%higher Top-1 accuracy on MobileNet-V2(4 bit),as compared to the HAQ and ZeroQ method.And our method can achieve 2.6%higher mAP on YOLOV3(6 bit),as compared to per-layer quantization method.