{"id":13685117,"url":"https://github.com/raspberrypi/pico-tflmicro","last_synced_at":"2025-05-15T09:05:30.955Z","repository":{"id":45742790,"uuid":"315409536","full_name":"raspberrypi/pico-tflmicro","owner":"raspberrypi","description":"Pico TensorFlow Lite Port","archived":false,"fork":false,"pushed_at":"2024-12-27T02:56:44.000Z","size":3646,"stargazers_count":686,"open_issues_count":7,"forks_count":101,"subscribers_count":40,"default_branch":"main","last_synced_at":"2025-04-03T04:09:39.674Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"C++","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/raspberrypi.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,"publiccode":null,"codemeta":null}},"created_at":"2020-11-23T18:46:42.000Z","updated_at":"2025-04-02T05:57:47.000Z","dependencies_parsed_at":"2022-08-12T12:10:24.936Z","dependency_job_id":"6003602f-9b8f-4815-b00b-0456a9d94c3c","html_url":"https://github.com/raspberrypi/pico-tflmicro","commit_stats":{"total_commits":45,"total_committers":4,"mean_commits":11.25,"dds":0.4444444444444444,"last_synced_commit":"03cbb1e7b89792aef2c59e2dbe8cb2c81c049bbd"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/raspberrypi%2Fpico-tflmicro","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/raspberrypi%2Fpico-tflmicro/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/raspberrypi%2Fpico-tflmicro/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/raspberrypi%2Fpico-tflmicro/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/raspberrypi","download_url":"https://codeload.github.com/raspberrypi/pico-tflmicro/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248166865,"owners_count":21058481,"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":"2024-08-02T14:00:44.203Z","updated_at":"2025-04-10T06:20:42.865Z","avatar_url":"https://github.com/raspberrypi.png","language":"C++","funding_links":[],"categories":["资源","C++","Resources"],"sub_categories":["项目","Projects"],"readme":"# TensorFlow Lite Micro\n\nAn Open Source Machine Learning Framework for Everyone.\n\n## Introduction\n\nThis is a version of the [TensorFlow Lite Micro library](https://www.tensorflow.org/lite/microcontrollers)\nfor the Raspberry Pi Pico microcontroller. It allows you to run machine \nlearning models to do things like voice recognition, detect people in images,\nrecognize gestures from an accelerometer, and other sensor analysis tasks.\nThis version has scripts to upstream changes from the Google codebase. It also\ntakes advantage of the RP2040's dual cores for increased speed on some \noperations.\n\n## Getting Started\n\nFirst you'll need to follow the Pico setup instructions to initialize the\ndevelopment environment on your machine. Once that is done, make sure that the\n`PICO_SDK_PATH` environment variable has been set to the location of the Pico\nSDK, either in the shell you're building in, or the CMake configure environment\nvariable setting of the extension if you're using VS Code.\n\nYou should then be able to build the library, tests, and examples. The easiest \nway to build is using VS Code's CMake integration, by loading the project and\nchoosing the build option at the bottom of the window.\n\nAlternatively you can build the entire project, including tests, by running the\nfollowing commands from a terminal once you're in this repo's directory:\n\n```bash\nmkdir build\ncd build\ncmake ..\nmake\n```\n\n## What's Included\n\nThere are several example applications included. The simplest one to begin with\nis the hello_world project. This demonstrates the fundamentals of deploying an \nML model on a device, driving the Pico's LED in a learned sine-wave pattern.\nOnce you have built the project, a UF2 file you can copy to the Pico should be\npresent at `build/examples/hello_world/hello_world.uf2`.\n\nAnother example is the person detector, but since the Pico doesn't come with\nimage inputs you'll need to write some code to hook up your own sensor. You can\nfind a fork of TFLM for the Arducam Pico4ML that does this at [arducam.com/pico4ml-an-rp2040-based-platform-for-tiny-machine-learning/](https://www.arducam.com/pico4ml-an-rp2040-based-platform-for-tiny-machine-learning/).\n\n## Contributing\n\nThis repository (https://github.com/raspberrypi/pico-tflmicro) is read-only,\nbecause it has been automatically generated from the master TensorFlow \nrepository at https://github.com/tensorflow/tensorflow. It's maintained by\n@petewarden on a best effort basis, so bugs and PRs may not get addressed. You\ncan generate an updated version of this generated project by running the command:\n\n```\nsync/sync_with_upstream.sh\n```\n\nThis should create a Pico-compatible project from the latest version of the\nTensorFlow repository.\n\n## Learning More\n\nThe [TensorFlow website](https://www.tensorflow.org/lite/microcontrollers) has\ninformation on training, tutorials, and other resources.\n\nThe [TinyML Book](https://tinymlbook.com) is a guide to using TensorFlow Lite Micro\nacross a variety of different systems.\n\n[TensorFlowLite Micro: Embedded Machine Learning on TinyML Systems](https://arxiv.org/pdf/2010.08678.pdf)\nhas more details on the design and implementation of the framework.\n\n## Licensing\n\nThe TensorFlow source code is covered by the Apache 2 license described in \nsrc/tensorflow/LICENSE, components from other libraries have the appropriate\nlicenses included in their third_party folders.","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fraspberrypi%2Fpico-tflmicro","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fraspberrypi%2Fpico-tflmicro","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fraspberrypi%2Fpico-tflmicro/lists"}