{"id":13628633,"url":"https://github.com/OAID/MXNet-HRT","last_synced_at":"2025-04-17T04:32:15.088Z","repository":{"id":108448421,"uuid":"96384683","full_name":"OAID/MXNet-HRT","owner":"OAID","description":"Heterogeneous Run Time version of MXNet. Added heterogeneous capabilities to the MXNet, uses heterogeneous computing infrastructure framework to speed up Deep Learning on Arm-based heterogeneous embedded platform. It also retains all the features of the original MXNet architecture which users deploy their applications seamlessly. ","archived":false,"fork":false,"pushed_at":"2018-02-11T02:54:44.000Z","size":28229,"stargazers_count":72,"open_issues_count":5,"forks_count":30,"subscribers_count":11,"default_branch":"master","last_synced_at":"2025-04-05T04:31:46.239Z","etag":null,"topics":["arm","arm-compute-library","arm-gpu","arm-neon","artificial-intelligence","cnn","dnn","machine-learning","mxnet","opencl"],"latest_commit_sha":null,"homepage":"","language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/OAID.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2017-07-06T03:30:23.000Z","updated_at":"2024-01-04T16:15:27.000Z","dependencies_parsed_at":null,"dependency_job_id":"fbb5e96c-9f68-4955-baf1-a19d252fb735","html_url":"https://github.com/OAID/MXNet-HRT","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OAID%2FMXNet-HRT","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OAID%2FMXNet-HRT/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OAID%2FMXNet-HRT/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/OAID%2FMXNet-HRT/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/OAID","download_url":"https://codeload.github.com/OAID/MXNet-HRT/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":249315973,"owners_count":21249868,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["arm","arm-compute-library","arm-gpu","arm-neon","artificial-intelligence","cnn","dnn","machine-learning","mxnet","opencl"],"created_at":"2024-08-01T22:00:54.697Z","updated_at":"2025-04-17T04:32:10.078Z","avatar_url":"https://github.com/OAID.png","language":"C++","funding_links":[],"categories":["\u003ca name=\"Tools\"\u003e\u003c/a\u003e13. Tools","\u003ca name=\"Tools\"\u003e\u003c/a\u003e9. Tools"],"sub_categories":["13.7 Deployment"],"readme":"# MXNet-HRT\n[![GitHub license](http://dmlc.github.io/img/apache2.svg)](./LICENSE)\n\nMXNet-HRT is a project that is maintained by **OPEN** AI LAB, it uses Arm Compute Library (NEON+GPU) to speed up [MXNet](https://mxnet.incubator.apache.org/) and provide utilities to debug, profile and tune application performance. \n\nThe release version is 0.3.1, is based on [Rockchip RK3399](http://www.rock-chips.com/plus/3399.html) Platform, target OS is Ubuntu 16.04. Can download the source code from [OAID/MXNet-HRT](https://github.com/OAID/MXNet-HRT)\n\n* The ARM Computer Vision and Machine Learning library is a set of functions optimised for both ARM CPUs and GPUs using SIMD technologies. See also [Arm Compute Library](https://github.com/ARM-software/ComputeLibrary).\n* MXNet is a Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more. See also [MXNet](https://github.com/apache/incubator-mxnet).\n\n### Documents\n* [Installation instructions](https://github.com/OAID/MXNet-HRT/blob/master/acl_openailab/installation.md)\n* [User Manuals PDF](https://github.com/OAID/MXNet-HRT/blob/master/acl_openailab/user_manual.pdf)\n* [Performance Report PDF](https://github.com/OAID/MXNet-HRT/blob/master/acl_openailab/performance_report.pdf)\n\n### Arm Compute Library Compatibility Issues :\nThere are some compatibility issues between ACL and MXNet Layers, we bypass it to MXNet's original layer class as the workaround solution for the below issues\n\n* Normalization in-channel issue\n* Tanh issue\n* Softmax supporting multi-dimension issue\n* Group issue\n\nPerformance need be fine turned in the future\n\n# Release History\nThe MXNet based version is [26b1cb9ad0bcde9206863a6f847455ff3ec3c266](https://github.com/apache/incubator-mxnet/tree/26b1cb9ad0bcde9206863a6f847455ff3ec3c266).\n\n## Version 0.3.1 - Feb 09, 2018\n\nSupport Arm Compute Library version 17.12\n\n## Version 0.3.0 - Jan 31, 2018\n\nSupport Arm Compute Library version 17.12\n\n## Version 0.2.0 - Aug 27, 2017\n\nSupport Arm Compute Library version 17.06 with 4 new layers added\n\n* Batch Normalization Layer\n* Direct convolution Layer\n* Concatenate layer\n\n\n## Version 0.1.0 - Jul 6, 2017 \n   \n  Initial version supports 10 Layers accelerated by Arm Compute Library version 17.05 : \n\n* Convolution Layer\n* Pooling Layer\n* LRN Layer\n* ReLU Layer\n* Sigmoid Layer\n* Softmax Layer\n* TanH Layer\n* AbsVal Layer\n* BNLL Layer\n* InnerProduct Layer\n\n\n# Issue Report\nEncounter any issue, please report on [issue report](https://github.com/OAID/MXNet-HRT/issues). Issue report should contain the following information :\n\n*  The exact description of the steps that are needed to reproduce the issue \n* The exact description of what happens and what you think is wrong \n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FOAID%2FMXNet-HRT","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FOAID%2FMXNet-HRT","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FOAID%2FMXNet-HRT/lists"}