{"id":20115398,"url":"https://github.com/amperecomputingai/aio-examples","last_synced_at":"2025-07-13T17:36:52.857Z","repository":{"id":43316457,"uuid":"426887060","full_name":"AmpereComputingAI/aio-examples","owner":"AmpereComputingAI","description":null,"archived":false,"fork":false,"pushed_at":"2024-03-05T12:33:47.000Z","size":6192,"stargazers_count":5,"open_issues_count":2,"forks_count":3,"subscribers_count":3,"default_branch":"tensorflow","last_synced_at":"2025-04-09T12:42:45.583Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AmpereComputingAI.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null}},"created_at":"2021-11-11T05:53:35.000Z","updated_at":"2024-12-06T00:10:15.000Z","dependencies_parsed_at":"2024-03-05T13:47:36.663Z","dependency_job_id":"6bd82a9a-2cc0-45d8-ac10-5271f7929b34","html_url":"https://github.com/AmpereComputingAI/aio-examples","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/AmpereComputingAI%2Faio-examples","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AmpereComputingAI%2Faio-examples/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AmpereComputingAI%2Faio-examples/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AmpereComputingAI%2Faio-examples/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AmpereComputingAI","download_url":"https://codeload.github.com/AmpereComputingAI/aio-examples/tar.gz/refs/heads/tensorflow","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252693712,"owners_count":21789747,"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":[],"created_at":"2024-11-13T18:35:04.963Z","updated_at":"2025-05-06T13:32:41.912Z","avatar_url":"https://github.com/AmpereComputingAI.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# aio-examples\n\nYou can try Tensorflow powered by AIO by either running jupyter notebook examples or python scripts on CLI level. \n\n**Note: Before running the examples, please run download_models.sh script to pull down all models.**\n\n## Running Jupyter Notebook QuickStart Examples\n\nUse AIO_NUM_THREADS to specify the number of cores the AIO compute kernels will run on\n```\nexport AIO_NUM_THREADS=16\ncd /aio-examples/\nbash download_models.sh\nbash start_notebook.sh\n```\n\nif you would like to run examples using with CLI you can run the start_notebook.sh in the background like so:\n\n```\nbash start_notebook.sh \u0026\n```\n\nIf you run it on a cloud instance, make sure your machine has port 8080 open and on your local device run:\n```\nssh -N -L 8080:localhost:8080 -i \u003cssh key\u003e your_user@xxx.xxx.xxx.xxx\n```\n\nUse a browser to point to the URL printed out by the Jupyter notebook launcher. You will find \nJupyter Notebook examples, examples.ipynb, under /classification and /object_detection folders.\nThe examples run through several inference models, visualize results and present the performance\nnumbers.\n\n## Running Examples With CLI\nTo use CLI-level scripts:\n\nUse AIO_NUM_THREADS to specify the number of cores the AIO compute kernels will run on\n```\nexport AIO_NUM_THREADS=16\ncd /aio-examples/\n```\n\nDownload the models:\n```\nbash download_models.sh\n```\n\nGo to the directory of choice, e.g.\n```\ncd classification/resnet_50_v15\n```\nEvaluate the model with run.py script\n\nOptional arguments:\n\n  -h, --help            show this help message and exit\n  \n  -m MODEL_PATH, --model_path MODEL_PATH\n                        \n  -p {fp32,fp16,int8}, --precision {fp32,fp16,int8}\n                        \n  -b BATCH_SIZE, --batch_size BATCH_SIZE\n\n```\npython run.py -m resnet_50_v15_tf_fp32.pb -p fp32\npython run.py -m resnet_50_v15_tflite_int8.tflite -p int8\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Famperecomputingai%2Faio-examples","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Famperecomputingai%2Faio-examples","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Famperecomputingai%2Faio-examples/lists"}