The TensorFlow Blog

TensorFlow Lite

TensorFlow Lite is an open source deep learning framework for on-device inference. Articles in this section cover deploying machine learning models on mobile and IoT devices.

Faster Dynamically Quantized Inference with XNNPack

AI · Announcement

Faster Dynamically Quantized Inference with XNNPack

अप्रैल 09, 2024 — Posted by Alan Kelly, Software EngineerWe are excited to announce that XNNPack’s Fully Connected and Convolution 2D operators now support dynamic range quantization. XNNPack is TensorFlow Lite’s CPU backend and CPUs deliver the widest reach for ML inference and remain the default target for TensorFlow Lite. Consequently, improving CPU inference performance is a top priority. We quadrupled inferen…

Half-precision Inference Doubles On-Device Inference Performance

AI · Announcement

Half-precision Inference Doubles On-Device Inference Performance

नवंबर 29, 2023 — Posted by Marat Dukhan and Frank Barchard, Software Engineers

Building a board game with the TFLite plugin for Flutter

Flutter · How To

Building a board game with the TFLite plugin for Flutter

अक्तूबर 18, 2023 — Posted by Wei Wei, Developer Advocate

Simpleperf case study: Fast initialization of TFLite’s Memory Arena

performance · reduce

Simpleperf case study: Fast initialization of TFLite’s Memory Arena

अगस्त 09, 2023 — Posted by Alan Kelly, Software Engineer

On-device fetal ultrasound assessment with TensorFlow Lite

AI · Health

On-device fetal ultrasound assessment with TensorFlow Lite

जून 20, 2023 — Posted by Angelica Willis and Akib Uddin, Health AI Team, Google Research

TensorFlow Lite Micro with ML acceleration

Coral · TensorFlow Lite

TensorFlow Lite Micro with ML acceleration

फ़रवरी 02, 2023 — Posted by Scott Main, Technical Writer, and the Coral team

New State-of-the-Art Quantized Models Added in TF Model Garden

TensorFlow Core · TensorFlow Lite

New State-of-the-Art Quantized Models Added in TF Model Garden

दिसंबर 22, 2022 — Posted by Jaehong Kim, Fan Yang, Shixin Luo, and Jiyang Kang

Community · TensorFlow Lite

Building a TensorFlow Lite based computer vision emoji input device with OpenMV

नवंबर 29, 2022 — A guest post by Sandeep Mistry, Arm

Community · TensorFlow Lite

Integrating Arm Virtual Hardware with the TensorFlow Lite Micro Continuous Integration Infrastructure

अक्तूबर 24, 2022 — A guest post by Matthias Hertel and Annie Tallund of Arm

Building a reinforcement learning agent with JAX, and deploying it on Android with TensorFlow Lite

Flax · JAX

Building a reinforcement learning agent with JAX, and deploying it on Android with TensorFlow Lite

अक्तूबर 03, 2022 — Posted by Wei Wei, Developer Advocate

mean · performance

Fast Reduce and Mean in TensorFlow Lite

सितंबर 30, 2022 — Posted by Alan Kelly, Software Engineer

Announcing TensorFlow Lite in Google Play Services General Availability

Android · TensorFlow Lite

Announcing TensorFlow Lite in Google Play Services General Availability

सितंबर 07, 2022 — Posted by Bernhard Bauer and Terry Heo, Software Engineers, Google

performance · profiling

Profiling XNNPACK with TFLite

जून 15, 2022 — Posted by Alan Kelly, Software Engineer

Adding Quantization-aware Training and Pruning to the TensorFlow Model Garden

TensorFlow Core · TensorFlow Lite

Adding Quantization-aware Training and Pruning to the TensorFlow Model Garden

जून 09, 2022 — Posted by Jaehong Kim, Rino Lee, and Fan Yang, Software Engineers

Memory-efficient inference with XNNPack weights cache

TensorFlow Lite

Memory-efficient inference with XNNPack weights cache

जून 06, 2022 — Posted by Zhi An Ng and Marat Dukhan, Google

TensorFlow Lite for education and makers

Coral · Education

TensorFlow Lite for education and makers

मई 17, 2022 — Posted by Scott Main, AIY Projects and Coral

TensorFlow Lite

On-device Text-to-Image Search with TensorFlow Lite Searcher Library

मई 11, 2022 — Posted by Zonglin Li, Lu Wang, Maxime Brénon, and Yuqi Li, Software Engineers

TensorFlow Lite

Video Classification on Edge Devices with TensorFlow Lite and MoViNet

अप्रैल 14, 2022 — Posted by Dan Kondratyuk, Liangzhe Yuan, Google Research and Khanh LeViet, TensorFlow Developer Relations

Accelerating TensorFlow Lite Micro on Cadence Audio Digital Signal Processors

TensorFlow Lite · tinyML

Accelerating TensorFlow Lite Micro on Cadence Audio Digital Signal Processors

मार्च 24, 2022 — Posted by Raj Pawate (Cadence) and Advait Jain (Google)

On-device one-shot learning for image classifiers with Classification-by-Retrieval

One-shot learning · TensorFlow Lite

On-device one-shot learning for image classifiers with Classification-by-Retrieval

जनवरी 18, 2022 — Posted by Zu Kim and Louis Romero, Software Engineers, Google Research

Tags