We present a post-training weight pruning method for deep neural networks
that achieves accuracy levels tolerable for the production setting and that is
sufficiently fast to be run on commodity hardware such as desktop CPUs or edge
devices. We propose a data-free extension of the approach for computer vision
models based on automatically-generated synthetic fractal images. We obtain
state-of-the-art results for data-free neural network pruning, with ~1.5% top@1
accuracy drop for a ResNet50 on ImageNet at 50% sparsity rate. When using real
data, we are able to get a ResNet50 model on ImageNet with 65% sparsity rate in
8-bit precision in a post-training setting with a ~1% top@1 accuracy drop. We
release the code as a part of the OpenVINO(TM) Post-Training Optimization tool.

本论文提出了一种用于深度神经网络的训练后权重修剪方法，其在生产环境中能够达到可接受的精度水平，并且足够快速以在桌面 CPU 或边缘设备等通用硬件上运行。该方法针对基于自动生成的合成分形图像的计算机视觉模型的无数据扩展，实现了数据免费的神经网络修剪，并在 ImageNet 数据集上获得了最新的数据免费神经网络修剪结果，对于 50％ 的稀疏率下使用 ResNet50 的 top@1 准确率丢失约为 1.5％。在使用真实数据时，能够获得在 8 位精度下稀疏率为 65％ 的 ResNet50 模型，而仅准确率下降约为 1％。

基于层间校准的深度神经网络剪枝方法

Post-training deep neural network pruning via layer-wise calibration

In this work we adapt multi-person pose estimation architecture to use it on
edge devices. We follow the bottom-up approach from OpenPose, the winner of
COCO 2016 Keypoints Challenge, because of its decent quality and robustness to
number of people inside the frame. With proposed network design and optimized
post-processing code the full solution runs at 28 frames per second (fps) on
Intel$\unicode{xAE}$ NUC 6i7KYB mini PC and 26 fps on Core$^{TM}$ i7-6850K CPU.
The network model has 4.1M parameters and 9 billions floating-point operations
(GFLOPs) complexity, which is just ~15% of the baseline 2-stage OpenPose with
almost the same quality. The code and model are available as a part of
Intel$\unicode{xAE}$ OpenVINO$^{TM}$ Toolkit.

本文将基于 OpenPose 的从下往上的方法适配多人姿态估计架构用于边缘设备，并提出了相应的网络设计和后处理代码优化，实现了 28fps 和 26fps 的帧率，模型参数为 4.1M，GFLOPs 为 9B，是基准 2 阶段 OpenPose 复杂度的 15% 。