PP-LCNet: A Lightweight CPU Convolutional Neural Network

TL;DR

PP-LCNet is a new lightweight CPU neural network that leverages MKLDNN to enhance accuracy across multiple tasks without increasing latency, outperforming existing models in classification and other vision tasks.

Contribution

Introduces PP-LCNet, a lightweight CPU network with improved accuracy and efficiency, utilizing MKLDNN acceleration and specific technological enhancements.

Findings

Outperforms state-of-the-art models in classification accuracy.

Maintains almost constant latency while improving accuracy.

Performs well in downstream tasks like object detection and semantic segmentation.

Abstract

We propose a lightweight CPU network based on the MKLDNN acceleration strategy, named PP-LCNet, which improves the performance of lightweight models on multiple tasks. This paper lists technologies which can improve network accuracy while the latency is almost constant. With these improvements, the accuracy of PP-LCNet can greatly surpass the previous network structure with the same inference time for classification. As shown in Figure 1, it outperforms the most state-of-the-art models. And for downstream tasks of computer vision, it also performs very well, such as object detection, semantic segmentation, etc. All our experiments are implemented based on PaddlePaddle. Code and pretrained models are available at PaddleClas.