{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/bmxnet-an-open-source-binary-neural-network","title":"BMXNet: An Open-Source Binary Neural Network Implementation Based on MXNet","arxiv_id":"1705.09864","date":"2017-05-27","proceeding":null,"authors":["Haojin Yang","Martin Fritzsche","Christian Bartz","Christoph Meinel"],"abstract":"Binary Neural Networks (BNNs) can drastically reduce memory size and accesses\nby applying bit-wise operations instead of standard arithmetic operations.\nTherefore it could significantly improve the efficiency and lower the energy\nconsumption at runtime, which enables the application of state-of-the-art deep\nlearning models on low power devices. BMXNet is an open-source BNN library\nbased on MXNet, which supports both XNOR-Networks and Quantized Neural\nNetworks. The developed BNN layers can be seamlessly applied with other\nstandard library components and work in both GPU and CPU mode. BMXNet is\nmaintained and developed by the multimedia research group at Hasso Plattner\nInstitute and released under Apache license. Extensive experiments validate the\nefficiency and effectiveness of our implementation. The BMXNet library, several\nsample projects, and a collection of pre-trained binary deep models are\navailable for download at https://github.com/hpi-xnor","url_abs":"http://arxiv.org/abs/1705.09864v1","url_pdf":"http://arxiv.org/pdf/1705.09864v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"bmxnet-an-open-source-binary-neural-network","repo_url":"https://github.com/hpi-xnor/BMXNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"mxnet","reach":{"status":"unanswered"}},{"paper_slug":"bmxnet-an-open-source-binary-neural-network","repo_url":"https://github.com/Jopyth/BMXNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"bmxnet-an-open-source-binary-neural-network","repo_url":"https://github.com/pminhtam/xnor_conv_pytorch_extension","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":null,"task_name":"CPU"},{"task_slug":null,"task_name":"GPU"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1705.09864","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}