AIBench Scenario: Scenario-distilling AI Benchmarking, BenchCouncil

 

Download User Manual

AIBench User Manual [AIBench-UserManual]

AIBench Download

Please cite our technical report when you publish results that you have obtained with AIBench:

AIBench: An Industry Standard AI Benchmark Suite from Internet Services. [Paper, Bibtex]
Fei Tang, Wanling Gao, Jianfeng Zhan, Chuanxin Lan, Xu Wen, Lei Wang, Chunjie Luo, Jiahui Dai, Zheng Cao, Xingwang Xiong, Zihan Jiang, Tianshu Hao, Fanda Fan, Fan Zhang, Yunyou Huang, Jianan Chen, Mengjia Du, Rui Ren, Chen Zheng, Daoyi Zheng, Haoning Tang, Kunlin Zhan, Biao Wang, Defei Kong, Minghe Yu, Chongkang Tan, Huan Li, Xinhui Tian, Yatao Li, Gang Lu, Junchao Shao, Zhenyu Wang, Xiaoyu Wang, Hainan Ye. Technical Report 2020. arXiv preprint arXiv: 2004.14690.

Full software packages of different implementations are available from the following links.

Download AIBench from BenchHub:

Download Datasets

Table 1: The Summary of Data Sets

data sets data size
1 CIFAR-10 60000 color images with the dimension of 32*32
2 ImageNet (1GB,10GB) ILSVRC2014 DET image dataset(unstructured image)
3 LSUN One million labelled images, classified into 10 scene categories and 20 object categories
4 MNIST handwritten digits database which has 60,000
training examples and 10,000 test examples(unstructured image)
5 MovieLens Dataset User’s score data for movies, which has 9,518,231
training examples and 386,835 test examples(semi-structured text)
6 WMT English-German WMT English-German translation dataset
7 MS COCO2014 A large-scale object detection, segmentation, and captioning dataset
8 Cityscapes A new large-scale dataset that contains a diverse set of stereo video sequences recorded in street scenes from 50 different cities
9 LibriSpeech A corpus of approximately 1000 hours of 16kHz read English speech
10 VGGFace2 A large-scale face recognition dataset
11 LFW dataset A database of face photographs
12 Robot pushing dataset 59,000 examples of robot pushing motions
13 ShapeNet Dataset A richly-annotated, large-scale dataset of 3D shapes
14 Gigaword Dataset Nearly ten million documents of the original English Gigaword Fifth Edition
15 Intellifusion data set 77,715 samples from 253 face IDs provided by Intellifusion

Download software

Download prerequisite software packages before using AIBench. Please refer to the user manual. The following packages should be installed firstly, and the running platform is Linux.

Software Version Download
TensorFlow 1.12 https://www.tensorflow.org
PyTorch 1.0.1 https://pytorch.org
GCC 4.8.2 http://gcc.gnu.org/releases.html