Tensorflow Lite Projects
AI Research Paper & Complete Technical Investigation
View Model Figures (4)
🧠 PyTorch 2.4 · Deep Learning · Academic Dossier · 2026

Tensorflow Lite Projects — Architecture & Technical Analysis

Comprehensive engineering investigation covering model architectures, mathematical loss formulations, stochastic data pipelines, and quantitative benchmarks.

3636
Verified Words
4
Model Figures
4.9★
Student Rating
PyTorch Implementation Model Backbone Loss Optimization Ablation Studies

Complete Technical Paper Content — Tensorflow Lite Projects

1. Executive Abstract, Problem Formulation & Background

Awesome TensorFlow Lite TensorFlow Lite is a set of tools that help convert and optimize TensorFlow models to run on mobile and edge devices. It's currently running on more than 4 billion devices! With TensorFlow 2.x, you can train a model with tf.Keras, easily convert a model to .tflite and deploy it; or you can download a pretrained TensorFlow Lite model from the model zoo. This is an awesome list of TensorFlow Lite models with sample apps, helpful tools and learning resources - Showcase what the community has built with TensorFlow Lite Put all the samples side-by-side for easy reference Share knowledge and learning resources Please submit a PR if you would like to contribute and follow the guidelines here . Contents Past announcements: Models with samples Computer vision Classification Detection Segmentation Style Transfer Generative Post estimation Other Text Speech Recommendation Game Model zoo TensorFlow Lite models TensorFlow models Ideas and Inspiration ML Kit examples Plugins and SDKs Helpful links Learning resources Blog posts Books Videos Podcasts MOOCs Past announcements: Here are some past feature annoucements of TensorFlow Lite: Announcement of the new converter - MLIR -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. Android Support Library - Makes mobile development easier ( Android sample code). Model Maker - Create your custom image & text classification models easily in a few lines of code. See below the Icon Classifier for a tutorial by the community. On-device training - It is finally here! Currently limited to transfer learning for image classification only but it's a great start. See the official Android sample code and another one from the community ( Blog | Android ). Hexagon delegate - 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 . Model Metadata - Provides a standard for model descriptions which also enables Code Gen and Android Studio ML Model Binding . Models with samples Here are the TensorFlow Lite models with app / device implementations, and references. Note: pretrained TensorFlow Lite models from MediaPipe are included, which you can implement with or without MediaPipe. Computer vision Classification Task Model App | Reference Source Classification MobileNetV1 ( download ) Android | iOS | Raspberry Pi | Overview tensorflow.org Classification MobileNetV2 Recognize Flowers on Android Codelab | Android TensorFlow team Classification MobileNetV2 Skin Lesion Detection Android Community Classification MobileNetV2 American Sign Language Detection | Colab Notebook | Android Community Classification CNN + Quantisation Aware Training Stone Paper Scissor Detection Colab Notebook | Flutter Community Classification EfficientNet-Lite0 ( download ) Icon Classifier Colab & Android | tutorial 1 | tutorial 2 Community Detection Task Model App | Reference Source Object detection Quantized COCO SSD MobileNet v1 ( download ) Android | iOS | Overview tensorflow.org Object detection YOLO Flutter | Paper Community Object detection YOLOv5 Yolov5 Inference Community Object detection MobileNetV2 SSD ( download ) Reference MediaPipe Object detection MobileDet ( Paper ) Blog post (includes the TFLite conversion process) MobileDet is from University of Wisconsin-Madison and Google and the blog post is from the Community License Plate detection SSD MobileNet (download) Flutter Community Face detection BlazeFace ( download ) Paper MediaPipe Face Authentication FaceNet Flutter Community Hand detection & tracking Palm detection & hand landmarks ( download ) Blog post | Model card | Android MediaPipe & Community Segmentation Task Model App | Reference Source Segmentation DeepLab V3 ( download ) Android & iOS | Overview | Flutter Image | Realtime | Paper tf.org & Community Segmentation Different variants of DeepLab V3 models Models on TF Hub with Colab Notebooks Community Segmentation DeepLab V3 model Android | Tutorial Community Hair Segmentation Download Paper MediaPipe Style Transfer Task Model App | Reference Source Style transfer Arbitrary image stylization Overview | Android | Flutter tf.org & Community Style transfer Better-quality style transfer models in .tflite Models on TF Hub with Colab Notebooks Community Video Style Transfer Download: Dynamic range models ) Android | Tutorial Community Segmentation & Style transfer DeepLabV3 & Style Transfer models Project repo | Android | Tutorial Community Generative Task Model App | Reference Source GANs U-GAT-IT (Selfie2Anime) Project repo | Android | Tutorial Community GANs White-box CartoonGAN ( download ) Project repo | Android | Tutorial Community GANs - Image Extrapolation Boundless on TF Hub Colab Notebook | Original Paper Community Post estimation Task Model App | Reference Source Pose estimation Posenet ( download ) Android | iOS | Overview tensorflow.org Pose Classification based Video Game Control MoveNet Lightning ( download ) Project Repository Community Other Task Model App | Reference Source Low-light image enhancement Models on TF Hub Project repo | Original Paper | Flutter OCR Models on TF Hub Project Repository Community Text Task Model Sample apps Source Question & Answer DistilBERT Android Hugging Face Text Generation GPT-2 / DistilGPT2 Android Hugging Face Text Classification Download Android | iOS | Flutter tf.org & Community Text Detection CRAFT Text Detector ( Paper ) Download | Project Repository | Blog1-Conversion to TFLite | Blog2-EAST vs CRAFT | Models on TF Hub | Android (Coming Soon) Community Text Detection EAST Text Detector ( Paper ) Models on TF Hub | Conversion and Inference Notebook Community Speech Task Model App | Reference Source Speech Recognition DeepSpeech Reference Mozilla Speech Recognition CONFORMER Inference Android Community Speech Synthesis Tacotron-2, FastSpeech2, MB-Melgan Android TensorSpeech Speech Synthesis(TTS) Tacotron2, FastSpeech2, MelGAN, MB-MelGAN, HiFi-GAN, Parallel WaveGAN Inference Notebook | Project Repository Community Recommendation Task Model App | Reference Source On-device Recommendation Dual-Encoder Android | iOS | Reference tf.org & Community Game Task Model App | Reference Source Game agent Reinforcement learning Flutter | Tutorial Community Model zoo TensorFlow Lite models These are the TensorFlow Lite models that could be implemented in apps and things: MobileNet - Pretrained MobileNet v2 and v3 models. TensorFlow Lite models TensorFlow Lite models - With official Android and iOS examples. Pretrained models - Quantized and floating point variants. TensorFlow Hub - Set "Model format = TFLite" to find TensorFlow Lite models. TensorFlow models These are TensorFlow models that could be converted to .tflite and then implemented in apps and things: TensorFlow models - Official TensorFlow models. Tensorflow detection model zoo - Pre-trained on COCO, KITTI, AVA v2.1, iNaturalist Species datasets. Ideas and Inspiration E2E TFLite Tutorials - 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. ML Kit examples ML Kit is a mobile SDK that brings Google's ML expertise to mobile developers. 2019-10-01 ML Kit Translate demo - A tutorial with material design Android (Kotlin) sample - recognize, identify Language and translate text from live camera with ML Kit for Firebase. 2019-03-13 Computer Vision with ML Kit - Flutter In Focus . 2019-02-09 Flutter + MLKit: Business Card Mail Extractor - A blog post with a Flutter sample code. 2019-02-08 From TensorFlow to ML Kit: Power your Android application with machine learning - A talk with Android (Kotlin) sample code. 2018-08-07 Building a Custom Machine Learning Model on Android with TensorFlow Lite . 2018-07-20 ML Kit and Face Detection in Flutter . 2018-07-27 ML Kit on Android 4: Landmark Detection . 2018-07-28 ML Kit on Android 3: Barcode Scanning . 2018-05-31 ML Kit on Android 2: Face Detection . 2018-05-22 ML Kit on Android 1: Intro . Plugins and SDKs Edge Impulse - Created by @EdgeImpulse to help you to train TensorFlow Lite models for embedded devices in the cloud. MediaPipe - A cross platform (mobile, desktop and Edge TPUs) AI pipeline by Google AI. (PM Ming Yong ) | MediaPipe examples . Coral Edge TPU - Edge hardware by Google. Coral Edge TPU examples . TensorFlow Lite Flutter Plugin - 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 . Helpful links Netron - A tool for visualizing models. AI benchmark - A website for benchmarking computer vision models on smartphones. Performance measurement - How to measure model performance on Android and iOS. Material design guidelines for ML - How to design machine learning powered features. A good example: ML Kit Showcase App . The People + AI Guide book - Learn how to design human-centered AI products. Adventures in TensorFlow Lite - A repository showing non-trivial conversion processes and general explorations in TensorFlow Lite. TFProfiler - An Android-based app to profile TensorFlow Lite models and measure its performance on smartphone. TensorFlow Lite for Microcontrollers TensorFlow Lite Examples - Android - A repository refactors and rewrites all the TensorFlow Lite Android examples which are included in the TensorFlow official website. Tensorflow-lite-kotlin-samples - A collection of Tensorflow Lite Android example Apps in Kotlin, to show different kinds of kotlin implementation of the example apps Learning resources Interested but not sure how to get started? Here are some learning resources that will help you whether you are a beginner or a practitioner in the field for a while. Blog posts 2021-11-09 On-device training in TensorFlow Lite 2021-09-27 Optical character recognition with TensorFlow Lite: A new example app 2021-06-16 https://blog.tensorflow.org/2021/06/easier-object-detection-on-mobile-with-tf-lite.html 2020-12-29 YOLOv3 to TensorFlow Lite Conversion - By Nitin Tiwari. 2020-04-20 What is new in TensorFlow Lite - By Khanh LeViet. 2020-04-17 Optimizing style transfer to run on mobile with TFLite - By Khanh LeViet and Luiz Gustavo Martins. 2020-04-14 How TensorFlow Lite helps you from prototype to product - By Khanh LeViet. 2019-11-08 Getting Started with ML on MCUs with TensorFlow - By Brandon Satrom. 2019-08-05 TensorFlow Model Optimization Toolkit — float16 quantization halves model size - By the TensorFlow team. 2018-07-13 Training and serving a real-time mobile object detector in 30 minutes with Cloud TPUs - By Sara Robinson, Aakanksha Chowdhery, and Jonathan Huang. 2018-06-11 - Why the Future of Machine Learning is Tiny - By Pete Warden. 2018-03-30 - Using TensorFlow Lite on Android ) - By Laurence Moroney. Books 2021-12-01 AI and Machine Learning On-Device Development (early access) - By Laurence Moroney ( @lmoroney ). 2020-10-01 AI and Machine Learning for Coders - By Laurence Moroney ( @lmoroney ). 2020-04-06 Mobile Deep Learning with TensorFlow Lite, ML Kit and Flutter : Build scalable real-world projects to implement end-to-end neural networks on Android and iOS ( GitHub ) - By Anubhav Singh ( @xprilion ) and Rimjhim Bhadani ( @Rimjhim28 ). 2020-03-01 Raspberry Pi for Computer Vision ( Complete Bundle | TOC ) - By the PyImageSearch Team: Adrian Rosebrock ( @PyImageSearch ), David Hoffman, Asbhishek Thanki, Sayak Paul ( @RisingSayak ), and David Mcduffee. 2019-12-01 TinyML - By Pete Warden ( @petewarden ) and Daniel Situnayake ( @dansitu ). 2019-10-01 Practical Deep Learning for Cloud, Mobile, and Edge - By Anirudh Koul ( @AnirudhKoul ), Siddha Ganju ( @SiddhaGanju ), and Meher Kasam ( @MeherKasam ). Videos 2021-10-06 Contributing to TensorFlow Lite with Sunit Roy (Hacktoberfest 2021) 2020-07-25 Android ML by Hoi Lam (GDG Kolkata meetup). 2020-04-01 Easy on-device ML from prototype to production (TF Dev Summit 2020). 2020-03-11 TensorFlow Lite: ML for mobile and IoT devices (TF Dev Summit 2020). 2019-10-31 Keynote - TensorFlow Lite: ML for mobile and IoT devices . 2019-10-31 TensorFlow Lite: Solution for running ML on-device . 2019-10-31 TensorFlow model optimization: Quantization and pruning . 2019-10-29 Inside TensorFlow: TensorFlow Lite . 2018-04-18 TensorFlow Lite for Android (Coding TensorFlow) . Podcasts 2020-08-08 Talking Machine Learning with Hoi Lam . MOOCs Introduction to TensorFlow Lite - Udacity course by Daniel Situnayake (@dansitu), Paige Bailey ( @DynamicWebPaige ), and Juan Delgado. Device-based Models with TensorFlow Lite - Coursera course by Laurence Moroney ( @lmoroney ). The Future of ML is Tiny and Bright - A series of edX courses created by Harvard in collaboration with Google. Instructors - Vijay Janapa Reddi, Laurence Moroney, and Pete Warden.

TensorFlow Lite is a set of tools that help convert and optimize TensorFlow models to run on mobile and edge devices. It's currently running on more than 4 billion devices! With TensorFlow 2.x, you can train a model with tf.Keras, easily convert a model to .tflite and deploy it; or you can download a pretrained TensorFlow Lite model from the model zoo.

This is an awesome list of TensorFlow Lite models with sample apps, helpful tools and learning resources -

Here are the TensorFlow Lite models with app / device implementations, and references. Note: pretrained TensorFlow Lite models from MediaPipe are included, which you can implement with or without MediaPipe.

These are TensorFlow models that could be converted to .tflite and then implemented in apps and things:

Interested but not sure how to get started? Here are some learning resources that will help you whether you are a beginner or a practitioner in the field for a while.

An awesome list of TensorFlow Lite models, samples, tutorials, tools and learning resources.

lutzroeder / netron Star 33.6k Visualizer for neural network, deep learning and machine learning models machine-learning ai deep-learning neural-network tensorflow numpy keras ml pytorch visualizer machinelearning deeplearning coreml onnx tensorflow-lite safetensors Updated Oct 28, 2026 JavaScript

2. Related Work, Literature Survey & Algorithmic Foundations

PINTO0309 / PINTO_model_zoo Sponsor Star 4.6k A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8), EdgeTPU, CoreML. caffe computer-vision model-zoo tensorflow model models keras pytorch pretrained-models coreml onnx tensorflow-lite tflite tensorflowjs tfjs openvino edgetpu mediapipe tflite-models tf-trt Updated Oct 24, 2026 Python

A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8), EdgeTPU, CoreML.

devzwy / open_nsfw_android Star 2k 🔥🔥🔥色情图片离线识别,基于TensorFlow实现。识别只需20ms,可断网测试,成功率99%,调用只要一行代码,从雅虎的开源项目open_nsfw移植,该模型文件可用于iOS、java、C++等平台 tensorflow nsfw tensorflow-models tensorflow-examples tensorflow-android tensorflow-gpu tensorflowlite pornography tensorflow-lite nsfw-android tensorflow-lite-nsfw nsfw-filter photographs-to-discern-yellow yellow-chart picture-recognition picture-recognition-sdk photo-recognition-sdk photo-recognition photo-identification Updated Apr 8, 2023 Java

🔥🔥🔥色情图片离线识别,基于TensorFlow实现。识别只需20ms,可断网测试,成功率99%,调用只要一行代码,从雅虎的开源项目open_nsfw移植,该模型文件可用于iOS、java、C++等平台

fangfufu / Linux-Fake-Background-Webcam Sponsor Star 1.7k Faking your webcam background under GNU/Linux, now supports background blurring, animated background, colour map effect, hologram effect and on-demand processing. webcam opencv-python v4l2loopback tensorflow-lite mediapipe akvcam webcam-background Updated Feb 24, 2026 Python

Faking your webcam background under GNU/Linux, now supports background blurring, animated background, colour map effect, hologram effect and on-demand processing.

Delta-ML / delta Star 1.6k DELTA is a deep learning based natural language and speech processing platform. LF AI & DATA Projects: https://lfaidata.foundation/projects/delta/ nlp front-end ops deep-learning text-classification tensorflow nlu speech inference text-generation speech-recognition seq2seq sequence-to-sequence speaker-verification asr tensorflow-serving emotion-recognition custom-ops serving tensorflow-lite Updated Apr 16, 2025 Python

DELTA is a deep learning based natural language and speech processing platform. LF AI & DATA Projects: https://lfaidata.foundation/projects/delta/

3. Dataset Ingestion, Preprocessing & Stochastic Augmentations

margaretmz / awesome-tensorflow-lite Star 1.4k An awesome list of TensorFlow Lite models, samples, tutorials, tools and learning resources. android ios awesome mobile computer-vision deep-learning model-zoo tensorflow sample-app awesome-list keras-tutorials flutter tensorflow-models mlkit tensorflow-lite tflite tfhub tensorflow-keras mediapipe tflite-models Updated Mar 1, 2022

An awesome list of TensorFlow Lite models, samples, tutorials, tools and learning resources.

tucan9389 / awesome-ml-demos-with-ios Sponsor Star 1.3k The challenge projects for Inferencing machine learning models on iOS ios demo machine-learning awesome tensorflow inference mlkit coreml tensorflow-lite Updated Mar 21, 2021 Python

qualcomm / ai-hub-models Star 1.2k Qualcomm® AI Hub Models is our collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices. machine-learning inference pytorch machinelearning deeplearning demos inference-engine onnx tensorflow-lite qnn inference-api Updated Oct 29, 2026 Python

Qualcomm® AI Hub Models is our collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices.

margelo / react-native-fast-tflite Star 1.2k 🧬 High-performance TensorFlow Lite library for React Native with GPU acceleration react fast react-native ai camera native tensorflow detection ml arraybuffer facial-recognition object-detection hacktoberfest tensorflow-lite tflite Updated Sep 11, 2026 TypeScript

PINTO0309 / onnx2tf Sponsor Star 1k A tool for converting ONNX files to LiteRT/TFLite/TensorFlow, PyTorch native code (nn.Module), TorchScript (.pt), state_dict (.pt), Exported Program (.pt2), and Dynamo ONNX. It also supports direct conversion from LiteRT to PyTorch. android docker machine-learning deep-learning tensorflow models keras pytorch transformer lstm quantization coreml onnx litert model-converter tensorflow-lite tflite tfjs torchscript Updated Sep 14, 2026 Python

A tool for converting ONNX files to LiteRT/TFLite/TensorFlow, PyTorch native code (nn.Module), TorchScript (.pt), state_dict (.pt), Exported Program (.pt2), and Dynamo ONNX. It also supports direct conversion from LiteRT to PyTorch.

4. Neural Network Backbone, Layer Specifications & Loss Formulations

asus4 / tf-lite-unity-sample Sponsor Star 961 TensorFlow Lite Samples on Unity machine-learning unity tensorflow-lite mediapipe Updated May 28, 2026 C#

amitshekhariitbhu / Android-TensorFlow-Lite-Example Star 772 Android TensorFlow Lite Machine Learning Example machine-learning deep-neural-networks deep-learning tensorflow machine-learning-algorithms tensorflow-tutorials tensorflow-examples android-example tensorflow-lite tflite Updated May 2, 2025 Java

anilsathyan7 / Portrait-Segmentation Star 667 Real-time portrait segmentation for mobile devices android tensorflow keras deeplearning deepstream deeplab jetson-tx2 portrait-matting opencv-dnn mobilenetv2 tensorflow-lite tensorflowjs unet-image-segmentation int8-inference edge-ai portrait-segmentation mediapipe color-harmonization coral-tpu gpu-delegate Updated Jan 17, 2021 Jupyter Notebook

terryky / tflite_gles_app Star 505 GPU accelerated deep learning inference applications for RaspberryPi / JetsonNano / Linux PC using TensorflowLite GPUDelegate / TensorRT raspberry-pi tensorflow opengles opengl-es tensorrt tensorflow-lite tflite handpose jetson-nano facemesh Updated Apr 22, 2022 C

GPU accelerated deep learning inference applications for RaspberryPi / JetsonNano / Linux PC using TensorflowLite GPUDelegate / TensorRT

qualcomm / ai-hub-apps Star 473 The Qualcomm® AI Hub apps are a collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices. machine-learning inference pytorch machinelearning deeplearning demos inference-engine onnx tensorflow-lite qnn inference-api Updated Oct 28, 2026 Python

The Qualcomm® AI Hub apps are a collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices.

Desert-Ant-Labs / desert-ant-core Star 428 On-device AI SDKs for iOS, macOS, Android, and the web. Small, focused models that run fully offline in Swift, Kotlin, and JavaScript with Core ML, LiteRT, and WebAssembly. nodejs javascript android kotlin macos swift ios machine-learning privacy typescript browser sdk offline webassembly inference coreml on-device litert tensorflow-lite edge-ai Updated Oct 27, 2026 Swift

5. Training Protocol, Convergence Behavior & Experimental Evaluation

On-device AI SDKs for iOS, macOS, Android, and the web. Small, focused models that run fully offline in Swift, Kotlin, and JavaScript with Core ML, LiteRT, and WebAssembly.

huggingface / tflite-android-transformers Star 421 DistilBERT / GPT-2 for on-device inference thanks to TensorFlow Lite with Android demo apps android nlp tensorflow transformers tensorflow-lite Updated Jul 25, 2023 Java

DistilBERT / GPT-2 for on-device inference thanks to TensorFlow Lite with Android demo apps

DeutscheKI / tevr-asr-tool Star 410 State-of-the-art (ranked #1 Aug 2022) German Speech Recognition in 284 lines of C++. This is a 100% private 100% offline 100% free CLI tool. c-plus-plus machine-learning deep-learning debian offline tensorflow speech speech-recognition private wave speech-to-text command-line-tool pretrained-models language-model asr debian-package kenlm tensorflow-lite german-speech-recognition no-cloud Updated Aug 9, 2022 C

State-of-the-art (ranked #1 Aug 2022) German Speech Recognition in 284 lines of C++. This is a 100% private 100% offline 100% free CLI tool.

iwatake2222 / play_with_tflite Star 381 Sample projects for TensorFlow Lite in C++ with delegates such as GPU, EdgeTPU, XNNPACK, NNAPI opencv deep-learning cpp tensorflow tensorflow-lite edgetpu Updated Jul 18, 2022 C++

Sample projects for TensorFlow Lite in C++ with delegates such as GPU, EdgeTPU, XNNPACK, NNAPI

magic-blue-smoke / Dual-Edge-TPU-Adapter Star 381 Dual Edge TPU Adapter to use it on a system with single PCIe port on m.2 A/B/E/M slot home-assistant m2 coral tpu tensorflow-lite tpu-benchmarks tpu-acceleration edge-ai edgetpu edge-tpu m2-module coral-tpu pcie-card pcie-interface Updated Oct 7, 2026

Model Figures & Evaluation Curves (4 Images)

Neural Architecture Diagram: Tensorflow Lite Projects
Neural Architecture Diagram: Tensorflow Lite Projects
Neural Architecture Diagram: Tensorflow Lite Projects
Neural Architecture Diagram: Tensorflow Lite Projects
Neural Architecture Diagram: Tensorflow Lite Projects
Neural Architecture Diagram: Tensorflow Lite Projects
Neural Architecture Diagram: Tensorflow Lite Projects
Neural Architecture Diagram: Tensorflow Lite Projects

Deep Learning Execution Pipeline

📥 Input Tensors
(Preprocessing)
→
⚡ Backbone
(Feature Extraction)
→
🧠 Latent Space
(Self-Attention)
→
🎯 Output Head
(Loss Optimization)