Search Results for author: Chunjie Luo

Found 14 papers, 2 papers with code

Heterologous Normalization

no code implementations29 Sep 2021 Chunjie Luo, Jianfeng Zhan, Lei Wang, Wanling Gao

Specifically, it calculates the mean like Batch Normalization to maintain the advantage of Batch Normalization.

Shift-and-Balance Attention

1 code implementation24 Mar 2021 Chunjie Luo, Jianfeng Zhan, Tianshu Hao, Lei Wang, Wanling Gao

The attention branch is gated using the Sigmoid function and multiplied by the feature map's trunk branch.

HPC AI500: Representative, Repeatable and Simple HPC AI Benchmarking

no code implementations25 Feb 2021 Zihan Jiang, Wanling Gao, Fei Tang, Xingwang Xiong, Lei Wang, Chuanxin Lan, Chunjie Luo, Hongxiao Li, Jianfeng Zhan

Recent years witness a trend of applying large-scale distributed deep learning algorithms (HPC AI) in both business and scientific computing areas, whose goal is to speed up the training time to achieve a state-of-the-art quality.

Image Classification Performance

FLBench: A Benchmark Suite for Federated Learning

no code implementations17 Aug 2020 Yuan Liang, Yange Guo, Yanxia Gong, Chunjie Luo, Jianfeng Zhan, Yunyou Huang

The goal is to build a machine learning model from the data sets distributed on multiple devices so-called an isolated data island, while keeping their data secure and private.

Federated Learning

Finet: Using Fine-grained Batch Normalization to Train Light-weight Neural Networks

no code implementations14 May 2020 Chunjie Luo, Jianfeng Zhan, Lei Wang, Wanling Gao

To build light-weight network, we propose a new normalization, Fine-grained Batch Normalization (FBN).

Comparison and Benchmarking of AI Models and Frameworks on Mobile Devices

no code implementations7 May 2020 Chunjie Luo, Xiwen He, Jianfeng Zhan, Lei Wang, Wanling Gao, Jiahui Dai

Due to increasing amounts of data and compute resources, deep learning achieves many successes in various domains.

AIBench Scenario: Scenario-distilling AI Benchmarking

no code implementations6 May 2020 Wanling Gao, Fei Tang, Jianfeng Zhan, Xu Wen, Lei Wang, Zheng Cao, Chuanxin Lan, Chunjie Luo, Xiaoli Liu, Zihan Jiang

We formalize a real-world application scenario as a Directed Acyclic Graph-based model and propose the rules to distill it into a permutation of essential AI and non-AI tasks, which we call a scenario benchmark.

Extended Batch Normalization

no code implementations12 Mar 2020 Chunjie Luo, Jianfeng Zhan, Lei Wang, Wanling Gao

To alleviate the problem caused by small batch size, extended batch normalization computes the standard deviation along the (N, C, H, W) dimensions, thus enlarges the number of samples from which the standard deviation is computed.

Image Classification

AIBench: An Industry Standard Internet Service AI Benchmark Suite

no code implementations13 Aug 2019 Wanling Gao, Fei Tang, Lei Wang, Jianfeng Zhan, Chunxin Lan, Chunjie Luo, Yunyou Huang, Chen Zheng, Jiahui Dai, Zheng Cao, Daoyi Zheng, Haoning Tang, Kunlin Zhan, Biao Wang, Defei Kong, Tong Wu, Minghe Yu, Chongkang Tan, Huan Li, Xinhui Tian, Yatao Li, Junchao Shao, Zhenyu Wang, Xiaoyu Wang, Hainan Ye

On the basis of the AIBench framework, abstracting the real-world data sets and workloads from one of the top e-commerce providers, we design and implement the first end-to-end Internet service AI benchmark, which contains the primary modules in the critical paths of an industry scale application and is scalable to deploy on different cluster scales.


HPC AI500: A Benchmark Suite for HPC AI Systems

no code implementations27 Jul 2019 Zihan Jiang, Wanling Gao, Lei Wang, Xingwang Xiong, Yuchen Zhang, Xu Wen, Chunjie Luo, Hainan Ye, Yunquan Zhang, Shengzhong Feng, Kenli Li, Weijia Xu, Jianfeng Zhan

In this paper, we propose HPC AI500 --- a benchmark suite for evaluating HPC systems that running scientific DL workloads.

BigDataBench: A Scalable and Unified Big Data and AI Benchmark Suite

no code implementations23 Feb 2018 Wanling Gao, Jianfeng Zhan, Lei Wang, Chunjie Luo, Daoyi Zheng, Xu Wen, Rui Ren, Chen Zheng, Xiwen He, Hainan Ye, Haoning Tang, Zheng Cao, Shujie Zhang, Jiahui Dai

On the basis of our previous work that identifies eight data motifs taking up most of the run time of a wide variety of big data and AI workloads, we propose a scalable benchmarking methodology that uses the combination of one or more data motifs---to represent diversity of big data and AI workloads.

Cosine Normalization: Using Cosine Similarity Instead of Dot Product in Neural Networks

1 code implementation20 Feb 2017 Chunjie Luo, Jianfeng Zhan, Lei Wang, Qiang Yang

We compare cosine normalization with batch, weight and layer normalization in fully-connected neural networks as well as convolutional networks on the data sets of MNIST, 20NEWS GROUP, CIFAR-10/100 and SVHN.

Cannot find the paper you are looking for? You can Submit a new open access paper.