jaeswift-website/api/data/awesomelist/margaretmz--awesome-tensorflow-lite.json

{"slug": "margaretmz--awesome-tensorflow-lite", "title": "Awesome Tensorflow Lite", "description": "An awesome list of TensorFlow Lite models, samples, tutorials, tools and learning resources.", "github_url": "https://github.com/margaretmz/awesome-tensorflow-lite", "stars": "960", "tag": "Computer Science", "entry_count": 35, "subcategory_count": 13, "subcategories": [{"name": "General", "parent": "", "entries": [{"name": "Past announcements:", "url": "#past-announcements", "description": ""}, {"name": "Models with samples", "url": "#models-with-samples", "description": ""}, {"name": "Model zoo", "url": "#model-zoo", "description": ""}, {"name": "Ideas and Inspiration", "url": "#ideas-and-inspiration", "description": ""}, {"name": "ML Kit examples", "url": "#ml-kit-examples", "description": ""}, {"name": "Plugins and SDKs", "url": "#plugins-and-sdks", "description": ""}, {"name": "Helpful links", "url": "#helpful-links", "description": ""}, {"name": "Learning resources", "url": "#learning-resources", "description": ""}, {"name": "Announcement of the new converter", "url": "https://groups.google.com/a/tensorflow.org/d/msg/tflite/Z_h7706dt8Q/sNrjPj4yGgAJ", "description": "[MLIR](https://medium.com/tensorflow/mlir-a-new-intermediate-representation-and-compiler-framework-beba999ed18d)-based and enables conversion of new classes of models such as Mask R-CNN and Mobile BERT etc., supports functional control flow and better error handling during conversion. Enabled by default in the nightly builds."}, {"name": "Android Support Library", "url": "https://github.com/tensorflow/tflite-support/tree/master/tensorflow_lite_support/java", "description": "Makes mobile development easier ([Android (⭐6.5k)](https://github.com/tensorflow/examples/blob/master/lite/examples/image_classification/android/EXPLORE_THE_CODE.md) sample code).", "stars": "274"}, {"name": "Model Maker", "url": "https://www.tensorflow.org/lite/guide/model_maker", "description": "Create your custom [image & text (⭐6.5k)](https://github.com/tensorflow/examples/tree/master/tensorflow_examples/lite/model_maker) classification models easily in a few lines of code. See below the Icon Classifier for a tutorial by the community."}, {"name": "On-device training", "url": "https://blog.tensorflow.org/2019/12/example-on-device-model-personalization.html", "description": "It is finally here! Currently limited to transfer learning for image classification only but it's a great start. See the official [Android (⭐6.5k)](https://github.com/tensorflow/examples/blob/master/lite/examples/model_personalization/README.md) sample code and another one from the community ([Blog](https://aqibsaeed.github.io/on-device-activity-recognition) | [Android (⭐52)](https://github.com/aqibsaeed/on-device-activity-recognition))."}, {"name": "Hexagon delegate", "url": "https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/g3doc/performance/hexagon_delegate.md", "description": "How to use the Hexagon Delegate to speed up model inference on mobile and edge devices. Also see blog post  [Accelerating TensorFlow Lite on Qualcomm Hexagon DSPs](https://blog.tensorflow.org/2019/12/accelerating-tensorflow-lite-on-qualcomm.html).", "stars": "169k"}, {"name": "Model Metadata", "url": "https://www.tensorflow.org/lite/convert/metadata", "description": "Provides a standard for model descriptions which also enables [Code Gen and Android Studio ML Model Binding](https://www.tensorflow.org/lite/inference_with_metadata/codegen)."}]}, {"name": "Computer vision", "parent": "Models with samples", "entries": []}, {"name": "Text", "parent": "Models with samples", "entries": []}, {"name": "Speech", "parent": "Models with samples", "entries": []}, {"name": "Recommendation", "parent": "Models with samples", "entries": []}, {"name": "Game", "parent": "Models with samples", "entries": []}, {"name": "TensorFlow Lite models", "parent": "Model zoo", "entries": [{"name": "MobileNet", "url": "https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/README.md", "description": "Pretrained MobileNet v2 and v3 models.", "stars": "75k"}]}, {"name": "TensorFlow models", "parent": "Model zoo", "entries": [{"name": "TensorFlow models", "url": "https://github.com/tensorflow/models/tree/master/official", "description": "Official TensorFlow models.", "stars": "75k"}, {"name": "Tensorflow detection model zoo", "url": "https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf2_detection_zoo.md", "description": "Pre-trained on COCO, KITTI, AVA v2.1, iNaturalist Species datasets.", "stars": "75k"}, {"name": "E2E TFLite Tutorials", "url": "https://github.com/ml-gde/e2e-tflite-tutorials", "description": "Checkout this repo for sample app ideas and seeking help for your tutorial projects. Once a project gets completed, the links of the TensorFlow Lite model(s), sample code and tutorial will be added to this awesome list.", "stars": "123"}, {"name": "Edge Impulse", "url": "https://www.edgeimpulse.com/", "description": "Created by [@EdgeImpulse](https://twitter.com/EdgeImpulse) to help you to train TensorFlow Lite models for embedded devices in the cloud."}, {"name": "MediaPipe", "url": "https://github.com/google/mediapipe", "description": "A cross platform (mobile, desktop and Edge TPUs) AI pipeline by Google AI. (PM [Ming Yong](https://twitter.com/realmgyong)) | [MediaPipe examples](https://mediapipe.readthedocs.io/en/latest/examples.html).", "stars": "19k"}, {"name": "Coral Edge TPU", "url": "https://coral.ai/", "description": "Edge hardware by Google. [Coral Edge TPU examples](https://coral.ai/examples/)."}, {"name": "TensorFlow Lite Flutter Plugin", "url": "https://github.com/am15h/tflite_flutter_plugin/", "description": "Provides a dart API similar to the TensorFlow Lite Java API for accessing TensorFlow Lite interpreter and performing inference in flutter apps. [tflite\\_flutter on pub.dev](https://pub.dev/packages/tflite_flutter).", "stars": "362"}, {"name": "Netron", "url": "https://github.com/lutzroeder/netron", "description": "A tool for visualizing models.", "stars": "20k"}, {"name": "AI benchmark", "url": "http://ai-benchmark.com/tests.html", "description": "A website for benchmarking computer vision models on smartphones."}, {"name": "Performance measurement", "url": "https://www.tensorflow.org/lite/performance/measurement", "description": "How to measure model performance on Android and iOS."}, {"name": "Material design guidelines for ML", "url": "https://material.io/collections/machine-learning/patterns-for-machine-learning-powered-features.html", "description": "How to design machine learning powered features. A good example: [ML Kit Showcase App (⭐488)](https://github.com/firebase/mlkit-material-android)."}, {"name": "The People + AI Guide book", "url": "https://pair.withgoogle.com/", "description": "Learn how to design human-centered AI products."}, {"name": "Adventures in TensorFlow Lite", "url": "https://github.com/sayakpaul/Adventures-in-TensorFlow-Lite", "description": "A repository showing non-trivial conversion processes and general explorations in TensorFlow Lite.", "stars": "137"}, {"name": "TFProfiler", "url": "https://github.com/iglaweb/TFProfiler", "description": "An Android-based app to profile TensorFlow Lite models and measure its performance on smartphone.", "stars": "26"}, {"name": "TensorFlow Lite for Microcontrollers", "url": "https://www.tensorflow.org/lite/microcontrollers", "description": ""}, {"name": "TensorFlow Lite Examples - Android", "url": "https://github.com/dailystudio/tensorflow-lite-examples-android", "description": "A repository refactors and rewrites all the TensorFlow Lite Android examples which are included in the TensorFlow official website.", "stars": "34"}, {"name": "Tensorflow-lite-kotlin-samples", "url": "https://github.com/SunitRoy2703/Tensorflow-lite-kotlin-samples", "description": "A collection of Tensorflow Lite Android example Apps in Kotlin, to show different kinds of kotlin implementation of the [example apps](https://www.tensorflow.org/lite/examples)", "stars": "25"}]}, {"name": "Blog posts", "parent": "Learning resources", "entries": []}, {"name": "Books", "parent": "Learning resources", "entries": []}, {"name": "Videos", "parent": "Learning resources", "entries": []}, {"name": "Podcasts", "parent": "Learning resources", "entries": []}, {"name": "MOOCs", "parent": "Learning resources", "entries": [{"name": "Introduction to TensorFlow Lite", "url": "https://www.udacity.com/course/intro-to-tensorflow-lite--ud190", "description": "Udacity course by Daniel Situnayake (@dansitu), Paige Bailey ([@DynamicWebPaige](https://twitter.com/DynamicWebPaige)), and Juan Delgado."}, {"name": "Device-based Models with TensorFlow Lite", "url": "https://www.coursera.org/learn/device-based-models-tensorflow", "description": "Coursera course by Laurence Moroney ([@lmoroney](https://twitter.com/lmoroney))."}, {"name": "The Future of ML is Tiny and Bright", "url": "https://www.edx.org/professional-certificate/harvardx-tiny-machine-learning", "description": "A series of edX courses created by Harvard in collaboration with Google. Instructors - Vijay Janapa Reddi, Laurence Moroney, and Pete Warden."}]}]}